diff --git a/.gitattributes b/.gitattributes
index 29880a18233033946ececcdddacc65d2a4a52e5f..734bdfe63f573b24c34e07b8d55ad280cdb20959 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -6450,3 +6450,27 @@ neuronxcc-2.15.143.0+e39249ad/MODULE_fbfe999e7918c5e3c314+39f12043/model.neff fi
 neuronxcc-2.15.128.0+56dc5a86/MODULE_1384aee4e828bcd1c687/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.15.128.0+56dc5a86/MODULE_ad62c560530518a4523f/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.15.128.0+56dc5a86/MODULE_fb5aa8e68ce47badf8db/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_01c540090ff8bced389b+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_0b08b19b4706a50917ba+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_10ff4d6a928b94472f16+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_1b62264e9a4966bfa0e4+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_21a5e6094f799eaf9413+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_3c7f47a5211f45696b45+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_3dbb2404de8d122cfb72+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_452de3ba481f27cd766e+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_48a5a5886c35331e113d+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_499ca495a71d3ecda4ec+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_67f2ec151ef567c93a66+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_686de18f172d024b3d29+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_6d4285f70d46d16f0d98+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_742fbf1379b1b37ffccc+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_8896ee5f087b4718eea3+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_a51bc33669478de21a96+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_ab26fd71fa3f5e9fa45b+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_adcba825ed1523ba8d12+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_bc4eef25d6686ad21908+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_bdab92f819266df89445+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_cb3ec814cbdbd1a9df1b+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_e1e1e3a85cd7a83e0dd1+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_e503bb548c30caa02b1a+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.303.0+d9f03cda/MODULE_ea4f2290b2fcba35e5fb+7ac4dbae/model.neff filter=lfs diff=lfs merge=lfs -text
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_159b8e04162fff0b5e0b+39f12043/compile_flags.json b/neuronxcc-2.15.143.0+e39249ad/MODULE_159b8e04162fff0b5e0b+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.143.0+e39249ad/MODULE_159b8e04162fff0b5e0b+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_159b8e04162fff0b5e0b+39f12043/model.done b/neuronxcc-2.15.143.0+e39249ad/MODULE_159b8e04162fff0b5e0b+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_159b8e04162fff0b5e0b+39f12043/model.hlo_module.pb b/neuronxcc-2.15.143.0+e39249ad/MODULE_159b8e04162fff0b5e0b+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..e01bee797d0e8da6f0c0a34882c56d8307966cd4
--- /dev/null
+++ b/neuronxcc-2.15.143.0+e39249ad/MODULE_159b8e04162fff0b5e0b+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae1d087bbf16c0740359a6b0f5087438a47e8485ee208ce22084f2617b62144a
+size 57038
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_159b8e04162fff0b5e0b+39f12043/model.neff b/neuronxcc-2.15.143.0+e39249ad/MODULE_159b8e04162fff0b5e0b+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b1ca8e642e0cccd992d8dd89be1402d4f0189cde
Binary files /dev/null and b/neuronxcc-2.15.143.0+e39249ad/MODULE_159b8e04162fff0b5e0b+39f12043/model.neff differ
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_1c17384445f02bb1c520+39f12043/compile_flags.json b/neuronxcc-2.15.143.0+e39249ad/MODULE_1c17384445f02bb1c520+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.143.0+e39249ad/MODULE_1c17384445f02bb1c520+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_1c17384445f02bb1c520+39f12043/model.done b/neuronxcc-2.15.143.0+e39249ad/MODULE_1c17384445f02bb1c520+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_1c17384445f02bb1c520+39f12043/model.hlo_module.pb b/neuronxcc-2.15.143.0+e39249ad/MODULE_1c17384445f02bb1c520+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..0849d3c16688d6578bb82885c74c4fd85eda6deb
--- /dev/null
+++ b/neuronxcc-2.15.143.0+e39249ad/MODULE_1c17384445f02bb1c520+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d488fce94d4a0e71d453fc1559922da327af9cb8c37f3b31c59a12e2e86533b
+size 69301
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_1c17384445f02bb1c520+39f12043/model.neff b/neuronxcc-2.15.143.0+e39249ad/MODULE_1c17384445f02bb1c520+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..a8b005265bd951af51715814d00fdd03b1f0df19
Binary files /dev/null and b/neuronxcc-2.15.143.0+e39249ad/MODULE_1c17384445f02bb1c520+39f12043/model.neff differ
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_a7a030e002b72284d2f7+39f12043/compile_flags.json b/neuronxcc-2.15.143.0+e39249ad/MODULE_a7a030e002b72284d2f7+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.143.0+e39249ad/MODULE_a7a030e002b72284d2f7+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_a7a030e002b72284d2f7+39f12043/model.done b/neuronxcc-2.15.143.0+e39249ad/MODULE_a7a030e002b72284d2f7+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_a7a030e002b72284d2f7+39f12043/model.hlo_module.pb b/neuronxcc-2.15.143.0+e39249ad/MODULE_a7a030e002b72284d2f7+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..8aa7814654a3d8f4d4af1266f90ceaf1b65d3502
--- /dev/null
+++ b/neuronxcc-2.15.143.0+e39249ad/MODULE_a7a030e002b72284d2f7+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f17585322c240dc8bd2253c69e65bad5d8bb2f8c871ed8c6f1cd9a4fbab9a27
+size 57056
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_a7a030e002b72284d2f7+39f12043/model.neff b/neuronxcc-2.15.143.0+e39249ad/MODULE_a7a030e002b72284d2f7+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..1136d0bbe1b2ac8bf0ba39f5df3b9f84d4534e07
Binary files /dev/null and b/neuronxcc-2.15.143.0+e39249ad/MODULE_a7a030e002b72284d2f7+39f12043/model.neff differ
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_b81ae95f77d4c1accaa5+39f12043/compile_flags.json b/neuronxcc-2.15.143.0+e39249ad/MODULE_b81ae95f77d4c1accaa5+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.143.0+e39249ad/MODULE_b81ae95f77d4c1accaa5+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_b81ae95f77d4c1accaa5+39f12043/model.hlo_module.pb b/neuronxcc-2.15.143.0+e39249ad/MODULE_b81ae95f77d4c1accaa5+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..a99cf19d086e4192cb46592630672dee0dda28d5
--- /dev/null
+++ b/neuronxcc-2.15.143.0+e39249ad/MODULE_b81ae95f77d4c1accaa5+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d30aaaa7c85357560266abb1cfe544de4c41cc57a341419477b5869776ed28
+size 66209
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_b81ae95f77d4c1accaa5+39f12043/model.log b/neuronxcc-2.15.143.0+e39249ad/MODULE_b81ae95f77d4c1accaa5+39f12043/model.log
new file mode 100644
index 0000000000000000000000000000000000000000..734168278e407877e71b6b1fb3e8fbdcab1db3aa
--- /dev/null
+++ b/neuronxcc-2.15.143.0+e39249ad/MODULE_b81ae95f77d4c1accaa5+39f12043/model.log
@@ -0,0 +1 @@
+Failed compilation with ['neuronx-cc', 'compile', '--target=trn1', '--framework=XLA', '/tmp/ubuntu/neuroncc_compile_workdir/e8af53ca-9784-4616-946c-44f1f821c144/model.MODULE_b81ae95f77d4c1accaa5+39f12043.hlo_module.pb', '--output', '/tmp/ubuntu/neuroncc_compile_workdir/e8af53ca-9784-4616-946c-44f1f821c144/model.MODULE_b81ae95f77d4c1accaa5+39f12043.neff', '--model-type=transformer', '--auto-cast=none', '--execute-repetition=1', '--verbose=35']: 2024-12-16T14:15:25Z [TEN404] (_dot.952) Internal tensorizer error: SundaISel:Verifier::No store before first load inst 3990 for tensor t3598 (inst:   float32<1 x 1> $3990 = tensorscalarptr_add(float32<1 x 1> TongaPSum partitions[0] float32 [1, 1] %3840[0,0], float32<1 x 1> TongaSB partitions[0] float32 [1, 1] %3598[0,0]) # id=3990, , src_id=None, instances=1 # dl = tensor_op_name: _add.179 | hlo_id: 1356 |  [[];[]] -> [[];[]] ) - Please open a support ticket at https://github.com/aws-neuron/aws-neuron-sdk/issues/new. You may also be able to obtain more information using the 'XLA_IR_DEBUG' and 'XLA_HLO_DEBUG' environment variables.
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_d029fb66a724c1553f2f+39f12043/compile_flags.json b/neuronxcc-2.15.143.0+e39249ad/MODULE_d029fb66a724c1553f2f+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.143.0+e39249ad/MODULE_d029fb66a724c1553f2f+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_d029fb66a724c1553f2f+39f12043/model.done b/neuronxcc-2.15.143.0+e39249ad/MODULE_d029fb66a724c1553f2f+39f12043/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_d029fb66a724c1553f2f+39f12043/model.hlo_module.pb b/neuronxcc-2.15.143.0+e39249ad/MODULE_d029fb66a724c1553f2f+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..39acba8f2fb8b651c20b6ee24b80c086914e799b
--- /dev/null
+++ b/neuronxcc-2.15.143.0+e39249ad/MODULE_d029fb66a724c1553f2f+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d52fd2f202ce379c427a8b52fbf13f84733b0d6f4af34f2a5980f887fc72bda
+size 55679
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_d029fb66a724c1553f2f+39f12043/model.neff b/neuronxcc-2.15.143.0+e39249ad/MODULE_d029fb66a724c1553f2f+39f12043/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..ee845b0540a68801da777f28d46b028e6d722f1b
Binary files /dev/null and b/neuronxcc-2.15.143.0+e39249ad/MODULE_d029fb66a724c1553f2f+39f12043/model.neff differ
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_ec079d43c779ced7e047+39f12043/compile_flags.json b/neuronxcc-2.15.143.0+e39249ad/MODULE_ec079d43c779ced7e047+39f12043/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..146361c3d3be9576d184ec08a57699cb27736489
--- /dev/null
+++ b/neuronxcc-2.15.143.0+e39249ad/MODULE_ec079d43c779ced7e047+39f12043/compile_flags.json
@@ -0,0 +1 @@
+["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_ec079d43c779ced7e047+39f12043/model.hlo_module.pb b/neuronxcc-2.15.143.0+e39249ad/MODULE_ec079d43c779ced7e047+39f12043/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..62bc6a51e85fc42457b6114fd2115c75b708f58d
--- /dev/null
+++ b/neuronxcc-2.15.143.0+e39249ad/MODULE_ec079d43c779ced7e047+39f12043/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16502c8a2a9e35806ce35afb05df98a44d15f6f9ec86d9ac005c34f65a22bf0b
+size 69041
diff --git a/neuronxcc-2.15.143.0+e39249ad/MODULE_ec079d43c779ced7e047+39f12043/model.log b/neuronxcc-2.15.143.0+e39249ad/MODULE_ec079d43c779ced7e047+39f12043/model.log
new file mode 100644
index 0000000000000000000000000000000000000000..b7fc95cff9f09930564a9f935af48b15c56e4b7b
--- /dev/null
+++ b/neuronxcc-2.15.143.0+e39249ad/MODULE_ec079d43c779ced7e047+39f12043/model.log
@@ -0,0 +1 @@
+Failed compilation with ['neuronx-cc', 'compile', '--target=trn1', '--framework=XLA', '/tmp/ubuntu/neuroncc_compile_workdir/ca2f2bf9-26a9-4c69-97f9-36019967036b/model.MODULE_ec079d43c779ced7e047+39f12043.hlo_module.pb', '--output', '/tmp/ubuntu/neuroncc_compile_workdir/ca2f2bf9-26a9-4c69-97f9-36019967036b/model.MODULE_ec079d43c779ced7e047+39f12043.neff', '--model-type=transformer', '--auto-cast=none', '--execute-repetition=1', '--verbose=35']: 2024-12-16T14:15:32Z [TEN404] (_dot.1004) Internal tensorizer error: SundaISel:Verifier::No store before first load inst 4353 for tensor t3956 (inst:   float32<1 x 1> $4353 = tensorscalarptr_add(float32<1 x 1> $4352, float32<1 x 1> TongaSB partitions[0] float32 [1, 1] %3956[0,0]) # id=4353, , src_id=None, instances=1 # dl = tensor_op_name: _add.182 | hlo_id: 1778 |  [[];[]] -> [[];[]] ) - Please open a support ticket at https://github.com/aws-neuron/aws-neuron-sdk/issues/new. You may also be able to obtain more information using the 'XLA_IR_DEBUG' and 'XLA_HLO_DEBUG' environment variables.
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/11cebcde130c1f5b8a5d.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/11cebcde130c1f5b8a5d.json
new file mode 100644
index 0000000000000000000000000000000000000000..fb20cbcaef8f7c418ef851ed911a1f99c086d12c
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/11cebcde130c1f5b8a5d.json
@@ -0,0 +1 @@
+{"apply_residual_connection_post_layernorm": false, "architectures": ["BloomForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "gradient_checkpointing": false, "hidden_dropout": 0.1, "hidden_size": 32, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "initializer_range": 0.02, "is_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "layer_norm_epsilon": 1e-05, "model_type": "bloom", "n_head": 4, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 3, "pretraining_tp": 1, "seq_length": 7, "slow_but_exact": true, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1024}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/481519fdaa82a5e9ca3c.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/481519fdaa82a5e9ca3c.json
new file mode 100644
index 0000000000000000000000000000000000000000..033873bd8db277e027b04afa9cd4fa3d9968fd84
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/481519fdaa82a5e9ca3c.json
@@ -0,0 +1 @@
+{"apply_residual_connection_post_layernorm": false, "architectures": ["BloomForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "gradient_checkpointing": false, "hidden_dropout": 0.1, "hidden_size": 32, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "initializer_range": 0.02, "is_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "layer_norm_epsilon": 1e-05, "model_type": "bloom", "n_head": 4, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 3, "pretraining_tp": 1, "seq_length": 7, "slow_but_exact": true, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1024}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/5276a012f2eefa9af6da.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/5276a012f2eefa9af6da.json
new file mode 100644
index 0000000000000000000000000000000000000000..9c9eaa8e57da335ac8e0a9a885e78aba1982a36f
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/5276a012f2eefa9af6da.json
@@ -0,0 +1 @@
+{"apply_residual_connection_post_layernorm": false, "architectures": ["BloomForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "gradient_checkpointing": false, "hidden_dropout": 0.1, "hidden_size": 32, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "initializer_range": 0.02, "is_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "layer_norm_epsilon": 1e-05, "model_type": "bloom", "n_head": 4, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 3, "pretraining_tp": 1, "seq_length": 7, "slow_but_exact": true, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1024}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/gpt2/gpt2/aa40852fa5208b294329.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/gpt2/gpt2/aa40852fa5208b294329.json
new file mode 100644
index 0000000000000000000000000000000000000000..38a1f5c668adbb328e9cfc18df405dc244af481b
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/gpt2/gpt2/aa40852fa5208b294329.json
@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/4b98629fe202b2140a00.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/4b98629fe202b2140a00.json
new file mode 100644
index 0000000000000000000000000000000000000000..b3ab9f15e766ae1fcf2e21dd0de760ec38550e45
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/4b98629fe202b2140a00.json
@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/af13e5d873398d00de9e.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/af13e5d873398d00de9e.json
new file mode 100644
index 0000000000000000000000000000000000000000..f5fd062bb91c5a66f95f04c758fcfd676d1663a3
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/af13e5d873398d00de9e.json
@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/d0a6fa1b6956a4d680fa.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/d0a6fa1b6956a4d680fa.json
new file mode 100644
index 0000000000000000000000000000000000000000..596b9e533d7074f379286253a8a544f3b98dde04
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/d0a6fa1b6956a4d680fa.json
@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Llama-3.1-8B-Instruct/d4873490f07d6364f226.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Llama-3.1-8B-Instruct/d4873490f07d6364f226.json
new file mode 100644
index 0000000000000000000000000000000000000000..e36d30c2e9980ce8a87112ff6c64b93f93480ed2
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Llama-3.1-8B-Instruct/d4873490f07d6364f226.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct", "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 1024, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/4811debc00fce09ac124.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/4811debc00fce09ac124.json
new file mode 100644
index 0000000000000000000000000000000000000000..2228329eb7440cf8a71a294b554ee24f07e7afa4
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/4811debc00fce09ac124.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 16, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/70df192a162dc76a8ba2.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/70df192a162dc76a8ba2.json
new file mode 100644
index 0000000000000000000000000000000000000000..675b167e821d794feabc266e678ef53a7fe2f5f7
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/70df192a162dc76a8ba2.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/b6900574c407686bc850.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/b6900574c407686bc850.json
new file mode 100644
index 0000000000000000000000000000000000000000..82a62e67a30ecc89b33690a9139b4e0fff8443c4
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/b6900574c407686bc850.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/b708ec372a7fc766d289.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/b708ec372a7fc766d289.json
new file mode 100644
index 0000000000000000000000000000000000000000..1999db08b87adf2ca6d8c8e837cc8691dd59a453
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/b708ec372a7fc766d289.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 128, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/d8df4e1c37e866f90233.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/d8df4e1c37e866f90233.json
new file mode 100644
index 0000000000000000000000000000000000000000..eb2d85740c439ebe45a8e9149acc152488a39415
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/d8df4e1c37e866f90233.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/e852034e61abed3bc0ba.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/e852034e61abed3bc0ba.json
new file mode 100644
index 0000000000000000000000000000000000000000..5ad72d88e337d999f94b290006195db94c09f980
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/e852034e61abed3bc0ba.json
@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/0dd9463a56ca665e0009.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/0dd9463a56ca665e0009.json
new file mode 100644
index 0000000000000000000000000000000000000000..11976629ed3f76051a2d230d9021dd03c7987ffc
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/0dd9463a56ca665e0009.json
@@ -0,0 +1 @@
+{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 8, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "is_decoder": true, "max_position_embeddings": 512, "model_type": "mistral", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "dacorvo/tiny-random-MistralForCausalLM", "checkpoint_revision": "81d453e3c8985649e9ee3d4c9378461029d1c73a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 32000}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/21ab9e45cd41b65fb4e0.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/21ab9e45cd41b65fb4e0.json
new file mode 100644
index 0000000000000000000000000000000000000000..e79ce2a076875690e85cb713376c19b6a74e308b
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/21ab9e45cd41b65fb4e0.json
@@ -0,0 +1 @@
+{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 8, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "is_decoder": true, "max_position_embeddings": 512, "model_type": "mistral", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "dacorvo/tiny-random-MistralForCausalLM", "checkpoint_revision": "81d453e3c8985649e9ee3d4c9378461029d1c73a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 32000}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/ec3b5393c3977096c001.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/ec3b5393c3977096c001.json
new file mode 100644
index 0000000000000000000000000000000000000000..e2d2f2d46c65e6b5f28fe4f5046856728fbd95cf
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/ec3b5393c3977096c001.json
@@ -0,0 +1 @@
+{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 8, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "is_decoder": true, "max_position_embeddings": 512, "model_type": "mistral", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "dacorvo/tiny-random-MistralForCausalLM", "checkpoint_revision": "81d453e3c8985649e9ee3d4c9378461029d1c73a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 32000}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mixtral/dacorvo/Mixtral-tiny/63d71adb49398ef365fe.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mixtral/dacorvo/Mixtral-tiny/63d71adb49398ef365fe.json
new file mode 100644
index 0000000000000000000000000000000000000000..c9b8633547d288b5bccad829952e5036cb93a618
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mixtral/dacorvo/Mixtral-tiny/63d71adb49398ef365fe.json
@@ -0,0 +1 @@
+{"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 1024, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mixtral/dacorvo/Mixtral-tiny/84e0c54d67bb0c2ff590.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mixtral/dacorvo/Mixtral-tiny/84e0c54d67bb0c2ff590.json
new file mode 100644
index 0000000000000000000000000000000000000000..e99cbcf3be1b81c16d4f1e4374efacf13023cc31
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mixtral/dacorvo/Mixtral-tiny/84e0c54d67bb0c2ff590.json
@@ -0,0 +1 @@
+{"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 1024, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mixtral/dacorvo/Mixtral-tiny/dfa5935d58cd292c0422.json b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mixtral/dacorvo/Mixtral-tiny/dfa5935d58cd292c0422.json
new file mode 100644
index 0000000000000000000000000000000000000000..1556ca373acb9de6b40b7f8a5a8a15e4bcded6c4
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/0_REGISTRY/0.0.28.dev0/inference/mixtral/dacorvo/Mixtral-tiny/dfa5935d58cd292c0422.json
@@ -0,0 +1 @@
+{"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 1024, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.16.303.0+d9f03cda", "num_cores": 8, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_01c540090ff8bced389b+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_01c540090ff8bced389b+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_01c540090ff8bced389b+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_01c540090ff8bced389b+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_01c540090ff8bced389b+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_01c540090ff8bced389b+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_01c540090ff8bced389b+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..4e98e0c855fa0e25cb96a4e7706f3d64100ed6c9
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_01c540090ff8bced389b+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae6bba5e76799bce81338669eab39b6f67989cebf3e30d0ed3bff2a98afc556
+size 331842
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_01c540090ff8bced389b+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_01c540090ff8bced389b+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..c25ae9784175e6b12739356e070462e065bb4650
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_01c540090ff8bced389b+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae241934369b4c671b6a1e3b5286933f850c24642730687b8c06a0bf6bda1ad1
+size 3206144
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0912ea9cf6fe9e1af454+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0912ea9cf6fe9e1af454+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0912ea9cf6fe9e1af454+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0912ea9cf6fe9e1af454+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0912ea9cf6fe9e1af454+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0912ea9cf6fe9e1af454+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0912ea9cf6fe9e1af454+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..a38307f4e7ae98ff1d4f753a3eae048130fa8e77
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0912ea9cf6fe9e1af454+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec9373f814ab03ecf1f250e2f08fa06127361ee356b1d62b3b34d4fc688b5261
+size 52661
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0912ea9cf6fe9e1af454+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0912ea9cf6fe9e1af454+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..982e6cf9b663965e12578b7adce8b7476d61ea37
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0912ea9cf6fe9e1af454+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0b08b19b4706a50917ba+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0b08b19b4706a50917ba+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0b08b19b4706a50917ba+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0b08b19b4706a50917ba+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0b08b19b4706a50917ba+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0b08b19b4706a50917ba+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0b08b19b4706a50917ba+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..b228bbd94246910d466415ed7391b6ad9a70e322
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0b08b19b4706a50917ba+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:376bbe53219bb85008e5cd4702ed2cb62dc11a22ce499d582735a227184c8101
+size 331842
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0b08b19b4706a50917ba+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0b08b19b4706a50917ba+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..e5a03c083be9931139e6254026e4d0cb3bee14d5
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0b08b19b4706a50917ba+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6a6d15af0cf4a6fa0cca4b0306385d0f594cae08274973cf1c963f731827ece
+size 3154944
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..4e3027e0c0011d0af390b27b2d6b9fc6c3a910c6
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa3bae5c2799f67d582ca6bb3e309052dc635f4bf1d601f3e9df4c83f1a8af3d
+size 131287
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..9955b59256b2d37fed87a4b07d6a52f981a7cf83
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..4e3027e0c0011d0af390b27b2d6b9fc6c3a910c6
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa3bae5c2799f67d582ca6bb3e309052dc635f4bf1d601f3e9df4c83f1a8af3d
+size 131287
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..27ea0d2cd303301d9bf792850e68b9777e0dbc7c
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_0d95eb3b3153bf26363d+7ac4dbae/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_10ff4d6a928b94472f16+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_10ff4d6a928b94472f16+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_10ff4d6a928b94472f16+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_10ff4d6a928b94472f16+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_10ff4d6a928b94472f16+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_10ff4d6a928b94472f16+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_10ff4d6a928b94472f16+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..d2ae4f62d05556d6ad77f105bb9257946028bb9c
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_10ff4d6a928b94472f16+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:167ab8586ac7af80a539d34957a02160350fbb10eed815e0256c0e862969e0ef
+size 446383
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_10ff4d6a928b94472f16+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_10ff4d6a928b94472f16+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..d5ef161ec9b668f7fd806622d47c2dffbbc6c916
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_10ff4d6a928b94472f16+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b19f88dcd3200a48fa1fb24c44b611a76dd6e74bed8aa724a51c038d87169b2
+size 36066304
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_1b62264e9a4966bfa0e4+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1b62264e9a4966bfa0e4+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1b62264e9a4966bfa0e4+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_1b62264e9a4966bfa0e4+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1b62264e9a4966bfa0e4+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_1b62264e9a4966bfa0e4+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1b62264e9a4966bfa0e4+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..4dbc67339af54122a9d7e863d4780e9b9d0130ca
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1b62264e9a4966bfa0e4+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568f6bd91cadbc97af49da57205ba3ed89ee8e0313002cef44cc9c6ec1f0f4c4
+size 331842
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_1b62264e9a4966bfa0e4+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1b62264e9a4966bfa0e4+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..5faadebeb8f1fb4665cedfe4d478b2f9921ee261
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1b62264e9a4966bfa0e4+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4de9d9ad69a790c80c3f4787396b8f0ae37426b1723a7208c06bc7176e74770
+size 3062784
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_1e8ba23f323fbda65b6a+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1e8ba23f323fbda65b6a+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1e8ba23f323fbda65b6a+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_1e8ba23f323fbda65b6a+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1e8ba23f323fbda65b6a+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_1e8ba23f323fbda65b6a+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1e8ba23f323fbda65b6a+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..3ff1e0648c53e5bda2c0b98c06a0674c945d83de
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1e8ba23f323fbda65b6a+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a79b9c9666bd5b4003aef21ef0ff0ede80d4f9283d0a496b3e8dc07e13f55ab
+size 57992
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_1e8ba23f323fbda65b6a+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1e8ba23f323fbda65b6a+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b98d8967bbb7a3ab3d0b0fe6140c78e0c16a7ee5
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1e8ba23f323fbda65b6a+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_1f1adb44fc3b68c754ba+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1f1adb44fc3b68c754ba+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1f1adb44fc3b68c754ba+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_1f1adb44fc3b68c754ba+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1f1adb44fc3b68c754ba+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_1f1adb44fc3b68c754ba+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1f1adb44fc3b68c754ba+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..fdff7ae675aa065ab75d6fe54ad6511fe14bc82b
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1f1adb44fc3b68c754ba+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b77e3968a3e8b0d3a322d8ba130c76c9b0d57e7dbe48fb7db69895f340cf9f5
+size 67150
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_1f1adb44fc3b68c754ba+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1f1adb44fc3b68c754ba+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b738e31a6428b4e82490560c9781c7573090b57b
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_1f1adb44fc3b68c754ba+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_21a5e6094f799eaf9413+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_21a5e6094f799eaf9413+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_21a5e6094f799eaf9413+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_21a5e6094f799eaf9413+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_21a5e6094f799eaf9413+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_21a5e6094f799eaf9413+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_21a5e6094f799eaf9413+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..22457a60184bcebc93fe409fc87c75ea76691114
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_21a5e6094f799eaf9413+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642f640a1086eb6d5336569f4ddfe8919a2bbeebe8845e9d81421dfefa395da7
+size 446383
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_21a5e6094f799eaf9413+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_21a5e6094f799eaf9413+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..6486dc827d320ad7a0f708581adc4ed752df9096
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_21a5e6094f799eaf9413+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac844f059dde1c2f9abe8c6add837f3cb5188612731220f2192717417ca8d06f
+size 36066304
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_2266b688ebc72e832f03+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_2266b688ebc72e832f03+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_2266b688ebc72e832f03+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_2266b688ebc72e832f03+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_2266b688ebc72e832f03+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_2266b688ebc72e832f03+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_2266b688ebc72e832f03+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..695cd4fe7bfcfe95b4479e55f7c294849bc2e6ad
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_2266b688ebc72e832f03+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:491d0cb0883c46d8e7cd391d4ae7856443daebdecd63275382c7a829a414666b
+size 54574
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_2266b688ebc72e832f03+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_2266b688ebc72e832f03+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..386b040b4910dd620e2f08a3da09daba78bd547c
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_2266b688ebc72e832f03+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_2e9bd9adb5251d055be2+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_2e9bd9adb5251d055be2+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_2e9bd9adb5251d055be2+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_2e9bd9adb5251d055be2+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_2e9bd9adb5251d055be2+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_2e9bd9adb5251d055be2+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_2e9bd9adb5251d055be2+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..7c0468ff147b67764e5e8784b9e40812c99e8419
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_2e9bd9adb5251d055be2+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e18e53e115de97128f6372f482c82c8efa2fb2d39626592e17d0ed8e36ae72d
+size 31086
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_2e9bd9adb5251d055be2+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_2e9bd9adb5251d055be2+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..ec1c833062bf40991d75afface9b8b0251e4a4d4
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_2e9bd9adb5251d055be2+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_35700c39cb62216b7a83+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_35700c39cb62216b7a83+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_35700c39cb62216b7a83+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_35700c39cb62216b7a83+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_35700c39cb62216b7a83+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_35700c39cb62216b7a83+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_35700c39cb62216b7a83+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..5c35bf444c74053f3e1874b76a89081a7d4ed1b9
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_35700c39cb62216b7a83+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce8dadc287fb28e19e8f968add62cc19a0ae0132ff49538b5a8f08d44fc4962
+size 1964
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_35700c39cb62216b7a83+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_35700c39cb62216b7a83+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..bb823e3c947844638636d564572a7c3568aaa288
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_35700c39cb62216b7a83+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_3c7f47a5211f45696b45+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_3c7f47a5211f45696b45+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_3c7f47a5211f45696b45+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_3c7f47a5211f45696b45+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_3c7f47a5211f45696b45+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_3c7f47a5211f45696b45+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_3c7f47a5211f45696b45+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..a10637c2bdfe7b7642fc1c8ac353b698310c46bf
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_3c7f47a5211f45696b45+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d57958b187be4a6449461f263c5803fc335791abea31e44d153805bee400e69
+size 331842
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_3c7f47a5211f45696b45+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_3c7f47a5211f45696b45+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..3201f9d9cdc155ae342caeea6c0cf311df26fb29
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_3c7f47a5211f45696b45+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b550a3155b296682163ac9f77c01d1288a528023bf981e9a50835cd5a33eb8dc
+size 3308544
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_3dbb2404de8d122cfb72+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_3dbb2404de8d122cfb72+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_3dbb2404de8d122cfb72+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_3dbb2404de8d122cfb72+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_3dbb2404de8d122cfb72+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_3dbb2404de8d122cfb72+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_3dbb2404de8d122cfb72+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..9eb52bf6a9001232943390b7395a626527f8d0d2
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_3dbb2404de8d122cfb72+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfb852e633f115ad7b341c9ccc1dc978dd54fb48599b75ee14893bbd9a5cf41
+size 446383
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_3dbb2404de8d122cfb72+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_3dbb2404de8d122cfb72+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..210f7b667f0a0aeb5d4d2cf82315b3da2e40fe9c
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_3dbb2404de8d122cfb72+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aedfab51e05a3ba2e890667e6e9a4a14bd21eca9569284290ec8111da1c2fe3
+size 36066304
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_452de3ba481f27cd766e+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_452de3ba481f27cd766e+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_452de3ba481f27cd766e+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_452de3ba481f27cd766e+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_452de3ba481f27cd766e+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_452de3ba481f27cd766e+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_452de3ba481f27cd766e+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..54131bc0a252505fc9254069538d6cd3fe5875d8
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_452de3ba481f27cd766e+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf5a2d5f371a1cdd6087e455968bb9fe342b84c07e19909d7f944a46f8b16102
+size 256787
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_452de3ba481f27cd766e+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_452de3ba481f27cd766e+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..61b50209321d6f8d717c86ed5689c452b241a522
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_452de3ba481f27cd766e+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5db1954b0133467a363e602e3f8cdb6c39587b2908908c134e9a8f0b1498a740
+size 3267584
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_48a5a5886c35331e113d+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_48a5a5886c35331e113d+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_48a5a5886c35331e113d+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_48a5a5886c35331e113d+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_48a5a5886c35331e113d+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_48a5a5886c35331e113d+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_48a5a5886c35331e113d+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..4a0e3c68e5e35d4c7e350d9c2de15c6447fee971
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_48a5a5886c35331e113d+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49921794cd5cefbccd6217548d15e5003e5737b046f92d47852e4c60cf34b5e8
+size 363734
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_48a5a5886c35331e113d+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_48a5a5886c35331e113d+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..2d46dd173e1257f7de98be9545ef79afbcd4a12a
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_48a5a5886c35331e113d+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d65ccadedee63206cc303528b254cc906ca665d0b38b71a0f334d9ec190069b1
+size 3974144
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_499ca495a71d3ecda4ec+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_499ca495a71d3ecda4ec+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_499ca495a71d3ecda4ec+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_499ca495a71d3ecda4ec+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_499ca495a71d3ecda4ec+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_499ca495a71d3ecda4ec+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_499ca495a71d3ecda4ec+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..06d748971feabb0417eee59cdb0431e260323728
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_499ca495a71d3ecda4ec+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b60f0c07097d3dc47fa57b926e34aeed930b57ac15c1d1d52db29334d1ed43
+size 363734
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_499ca495a71d3ecda4ec+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_499ca495a71d3ecda4ec+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..ee4bf75e16d117fe3f5b9fc7050ae71e13113d86
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_499ca495a71d3ecda4ec+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c30a03f2954b4b94deda84215822224df0f641800c28a4e5002e3c17df01ed0
+size 6073344
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4bdb5562d9c1e3455798+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4bdb5562d9c1e3455798+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4bdb5562d9c1e3455798+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4bdb5562d9c1e3455798+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4bdb5562d9c1e3455798+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4bdb5562d9c1e3455798+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4bdb5562d9c1e3455798+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..05af0d1fc1ce4ecb96dda1102dd712c4d9337a6d
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4bdb5562d9c1e3455798+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116e2653fd99c793c9ffe6babd5df20ffaa65fc9de34123e801a2401dd1704e7
+size 54834
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4bdb5562d9c1e3455798+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4bdb5562d9c1e3455798+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..765a247adf3aa371a01e5b47295db50fb44712fa
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4bdb5562d9c1e3455798+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4ccc3dc5f7e4483232ca+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4ccc3dc5f7e4483232ca+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4ccc3dc5f7e4483232ca+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4ccc3dc5f7e4483232ca+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4ccc3dc5f7e4483232ca+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4ccc3dc5f7e4483232ca+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4ccc3dc5f7e4483232ca+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..31f3e0069cb71744e33cf38cb9bc00bcf23b2d7e
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4ccc3dc5f7e4483232ca+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c5d1658554dcc0a371038380e70caea57bff16e9a4da218df3aa25e8723ba8
+size 52342
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4ccc3dc5f7e4483232ca+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4ccc3dc5f7e4483232ca+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..30b712cabae73fd2eea5a810a5e4ef18251dd418
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4ccc3dc5f7e4483232ca+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4e97fbebcc16e113c928+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4e97fbebcc16e113c928+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4e97fbebcc16e113c928+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4e97fbebcc16e113c928+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4e97fbebcc16e113c928+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4e97fbebcc16e113c928+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4e97fbebcc16e113c928+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..7df45370884bef5e18014a50d824c675e786424d
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4e97fbebcc16e113c928+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e18d77f40a6780e86ad9c749af465291ba901dad3a54defa6853e44bbbb0c8
+size 20458
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4e97fbebcc16e113c928+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4e97fbebcc16e113c928+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..7b0556a389687aac1f0f922b2b2a100eed4f4ff2
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4e97fbebcc16e113c928+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4f3d1c597a20c208ad31+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4f3d1c597a20c208ad31+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4f3d1c597a20c208ad31+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4f3d1c597a20c208ad31+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4f3d1c597a20c208ad31+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4f3d1c597a20c208ad31+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4f3d1c597a20c208ad31+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..fa864570beb2f2d55d620253f17600fe095e3a9a
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4f3d1c597a20c208ad31+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e122214f89952ec786f0a4a44cfad919d9c326f2dbc36a78620f80c70081cd16
+size 32349
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_4f3d1c597a20c208ad31+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4f3d1c597a20c208ad31+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..7eb6fd6667bc5671b0ec93a5f335636d85e05a9e
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_4f3d1c597a20c208ad31+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..68560b60882cce44320adf9433eb30999e0f1468
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520d9f3cd41b5a0f6d54a9d4bf52be7a9b7ed0a6489b00a28ef6490ef03c902c
+size 131287
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..f85d45c9fa7aa72ae6318638ef243f2c5682c93b
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..68560b60882cce44320adf9433eb30999e0f1468
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520d9f3cd41b5a0f6d54a9d4bf52be7a9b7ed0a6489b00a28ef6490ef03c902c
+size 131287
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b3371e33ff48b77e1275fe3f07a1568845e25ff4
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_52bfb1f696156d741160+7ac4dbae/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_619cc5230b6bd099529d+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_619cc5230b6bd099529d+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_619cc5230b6bd099529d+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_619cc5230b6bd099529d+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_619cc5230b6bd099529d+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_619cc5230b6bd099529d+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_619cc5230b6bd099529d+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..21043a6c349da3257a03c3c80120362798998457
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_619cc5230b6bd099529d+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b271a972803d4d9e85d866768347a75e80903c260136a0440065272a3d1908
+size 40917
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_619cc5230b6bd099529d+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_619cc5230b6bd099529d+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..8937eb9e5093f962411bff83189d7ef2170fcdbd
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_619cc5230b6bd099529d+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_67f2ec151ef567c93a66+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_67f2ec151ef567c93a66+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_67f2ec151ef567c93a66+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_67f2ec151ef567c93a66+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_67f2ec151ef567c93a66+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_67f2ec151ef567c93a66+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_67f2ec151ef567c93a66+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..b91f41b48a0fa02bc3bf9377454a40112048c4e0
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_67f2ec151ef567c93a66+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b684f56505a6954b8b919a2558fa45db20b210a5707b8bd5c645adfe94a5b9
+size 446927
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_67f2ec151ef567c93a66+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_67f2ec151ef567c93a66+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..684d53a6f983bc4cbe3e41c537718c0a54bb2025
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_67f2ec151ef567c93a66+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ea884fe3fe98cb6875c9797a5984e093fd266ef8b93a7318f321d59fc848bd
+size 36076544
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_686de18f172d024b3d29+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_686de18f172d024b3d29+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_686de18f172d024b3d29+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_686de18f172d024b3d29+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_686de18f172d024b3d29+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_686de18f172d024b3d29+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_686de18f172d024b3d29+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..a5afd78d74bbd5a303c828f18f1687314ee0db92
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_686de18f172d024b3d29+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca801e1d50918cb4aa41131bb7471e62345160f1d1439651dcf0d942073c7f5
+size 363734
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_686de18f172d024b3d29+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_686de18f172d024b3d29+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..383eae2668968e8bb8d8e149373e3efad605d9f1
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_686de18f172d024b3d29+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8e1b48b9363cc07214b64bb8797f11bdec3412ddcc90912887cbd9d3255b6f
+size 4209664
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_6d4285f70d46d16f0d98+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_6d4285f70d46d16f0d98+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_6d4285f70d46d16f0d98+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_6d4285f70d46d16f0d98+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_6d4285f70d46d16f0d98+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_6d4285f70d46d16f0d98+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_6d4285f70d46d16f0d98+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..df65d9ea7f67bc384726d0fb228218bd3f6f3a74
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_6d4285f70d46d16f0d98+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59b78e728442287111d21ab8e531e570e6b57768b81a0922173d232f2dcec95
+size 363734
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_6d4285f70d46d16f0d98+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_6d4285f70d46d16f0d98+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..50054aa8cfb1016bd2841fabd8e9b34136a5b91f
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_6d4285f70d46d16f0d98+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d868692aa7128b84a3ddabe9ed5a70fa476acfee3ffe2bcc9aa9f9bf65f0e53
+size 4834304
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_6dc904710bf49cd0585d+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_6dc904710bf49cd0585d+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_6dc904710bf49cd0585d+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_6dc904710bf49cd0585d+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_6dc904710bf49cd0585d+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_6dc904710bf49cd0585d+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_6dc904710bf49cd0585d+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..74a50fb3d0726fd4c77c900587d39a269bb5c913
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_6dc904710bf49cd0585d+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e81e3eac1095a3052bc9ecbaee836118959ac7ac6d50b69b1597e5110ab8ba1
+size 31270
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_6dc904710bf49cd0585d+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_6dc904710bf49cd0585d+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..f0b94954320b94264ef14e14f3e0ab8cb458df6e
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_6dc904710bf49cd0585d+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_71793eda9b576e907e63+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_71793eda9b576e907e63+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_71793eda9b576e907e63+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_71793eda9b576e907e63+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_71793eda9b576e907e63+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_71793eda9b576e907e63+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_71793eda9b576e907e63+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..cbca0919044de54ef8c82c93bf75daf1ff121c5c
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_71793eda9b576e907e63+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a829947471d031088eaa10211d0a405d326bef186651a44a9b57be517d4f0839
+size 69984
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_71793eda9b576e907e63+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_71793eda9b576e907e63+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..8cd80418cddaa6b80145d27be3f6b84c1523ca74
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_71793eda9b576e907e63+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_742fbf1379b1b37ffccc+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_742fbf1379b1b37ffccc+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_742fbf1379b1b37ffccc+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_742fbf1379b1b37ffccc+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_742fbf1379b1b37ffccc+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_742fbf1379b1b37ffccc+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_742fbf1379b1b37ffccc+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..dc5164382dc57b5568afb64001cd262480cb8693
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_742fbf1379b1b37ffccc+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05e988aba9d5afa9ab0dd3a1cb8ddae362fb25e3e841d332b69e0141e63dc84
+size 256787
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_742fbf1379b1b37ffccc+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_742fbf1379b1b37ffccc+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..0e806145b866b76ff31f951f01e33922a587809f
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_742fbf1379b1b37ffccc+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66bb36e092153ce327823e40a543fce18e4fe03d8e454ff837de130826aecc0f
+size 5315584
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_83cc2c0995627023cedc+8a3305d3/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_83cc2c0995627023cedc+8a3305d3/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..2b12c328588df6955322fd03473d7e93dc523be6
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_83cc2c0995627023cedc+8a3305d3/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=5"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_83cc2c0995627023cedc+8a3305d3/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_83cc2c0995627023cedc+8a3305d3/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_83cc2c0995627023cedc+8a3305d3/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_83cc2c0995627023cedc+8a3305d3/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..cebcba0ca93d39fdbd30369351e58ea388bf5443
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_83cc2c0995627023cedc+8a3305d3/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b9a6143d98f7620325ba07f300adeb9234fc167ed360cc5f3f2385735dcf004
+size 9571
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_83cc2c0995627023cedc+8a3305d3/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_83cc2c0995627023cedc+8a3305d3/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..1a77385e0dfe69bcc4fd189df16b423ef92d4fe8
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_83cc2c0995627023cedc+8a3305d3/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..7b43a73011d34def3796ba54cdfddf05e50f08a9
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5883bbfc15486f379d522cddc24cfc6478c0aa6cf2afc27df4ae7095f8d638eb
+size 131287
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..6d7d414fdac42779c9eee86d3c8d698483147b5f
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..7b43a73011d34def3796ba54cdfddf05e50f08a9
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5883bbfc15486f379d522cddc24cfc6478c0aa6cf2afc27df4ae7095f8d638eb
+size 131287
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..1208366840235979ac4222c6b107b80c44906d8e
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_856e0cafdab1523c0eba+7ac4dbae/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_8896ee5f087b4718eea3+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_8896ee5f087b4718eea3+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_8896ee5f087b4718eea3+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_8896ee5f087b4718eea3+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_8896ee5f087b4718eea3+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_8896ee5f087b4718eea3+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_8896ee5f087b4718eea3+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..53187413e362a40b51a247972a3ad04a20a7241c
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_8896ee5f087b4718eea3+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ae8a7b1f88b45e6b2b58602bc8450a300b744af8fa78aa455d8d74230db0cf
+size 446383
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_8896ee5f087b4718eea3+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_8896ee5f087b4718eea3+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..e3f311c2f5c204a1fee243c8371b8f4ccf691a36
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_8896ee5f087b4718eea3+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:176509f7c5b373b9da3fea2ed3b1692798c5bca6383dc04b6064e6546dd5ca46
+size 36066304
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_8a1fb1c327ec592a8748+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_8a1fb1c327ec592a8748+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_8a1fb1c327ec592a8748+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_8a1fb1c327ec592a8748+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_8a1fb1c327ec592a8748+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_8a1fb1c327ec592a8748+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_8a1fb1c327ec592a8748+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..d601717a33819a8732c8eb821e768685c1a93f9e
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_8a1fb1c327ec592a8748+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2967e3b5f4c2f681bd99b61f84e051eee8a8bf8bba2ec05ad1b687cbde275ff1
+size 56615
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_8a1fb1c327ec592a8748+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_8a1fb1c327ec592a8748+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..9973d6da8f37ea3511dab77a27e28cd6cd0d060b
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_8a1fb1c327ec592a8748+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_a51bc33669478de21a96+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_a51bc33669478de21a96+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_a51bc33669478de21a96+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_a51bc33669478de21a96+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_a51bc33669478de21a96+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_a51bc33669478de21a96+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_a51bc33669478de21a96+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..9a69aa92af87cb7f47f94989cedac0f2515c52ac
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_a51bc33669478de21a96+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:485316cc071b1de9efa115afdb21bf98714c36e55d34efa77e3947db81e827f5
+size 363734
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_a51bc33669478de21a96+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_a51bc33669478de21a96+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..856008f08ed2781be392e5c47ad896b2790ead67
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_a51bc33669478de21a96+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b295bd1d9c4fb5ad46a97556feb0aa566d9f545bd7804fccc7742b6e95f6e7f2
+size 4547584
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_a98da7627c60f9897da5+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_a98da7627c60f9897da5+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_a98da7627c60f9897da5+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_a98da7627c60f9897da5+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_a98da7627c60f9897da5+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_a98da7627c60f9897da5+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_a98da7627c60f9897da5+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..c6f150c1394af52336eba00e192afb6661fd2b8a
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_a98da7627c60f9897da5+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faeb2142abe35b1b45be1731e371b7cb2dadc151e6d1085f9db3f34eb390c2f8
+size 2060
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_a98da7627c60f9897da5+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_a98da7627c60f9897da5+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..f8bac6fe37bb61e55ad0fe66f9ea828a0e7fe274
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_a98da7627c60f9897da5+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ab26fd71fa3f5e9fa45b+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ab26fd71fa3f5e9fa45b+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ab26fd71fa3f5e9fa45b+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ab26fd71fa3f5e9fa45b+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ab26fd71fa3f5e9fa45b+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ab26fd71fa3f5e9fa45b+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ab26fd71fa3f5e9fa45b+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..dd3a0db10c69263d127457c4bd41a049afc8d072
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ab26fd71fa3f5e9fa45b+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c92e5dab4ddb6c6500ffda0f1f8acd5486acb86315d84510db8d3c60a51da4
+size 256787
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ab26fd71fa3f5e9fa45b+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ab26fd71fa3f5e9fa45b+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..3708c746e6b5881bf1421e139069771ac21f5a35
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ab26fd71fa3f5e9fa45b+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de32a23ee257144bb7539e442258755f9be5aef0684e2cea2c2e8f612f3fb981
+size 3830784
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_adcba825ed1523ba8d12+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_adcba825ed1523ba8d12+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_adcba825ed1523ba8d12+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_adcba825ed1523ba8d12+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_adcba825ed1523ba8d12+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_adcba825ed1523ba8d12+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_adcba825ed1523ba8d12+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..7e7eaac11d7e67ccc629f4ce271b496fb82ee58a
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_adcba825ed1523ba8d12+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218f202dbce0c502b751f64c4232a1ccecf3522146920a8374e7b651aeb7b337
+size 331842
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_adcba825ed1523ba8d12+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_adcba825ed1523ba8d12+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..69a7d10d7ff3bda3096ef905f02d35af793d2e11
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_adcba825ed1523ba8d12+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa844b1253c576b7caf46c6ae478e9229897feeca863173feb8ad080e783095b
+size 3103744
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_b340826080c529da9625+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_b340826080c529da9625+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_b340826080c529da9625+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_b340826080c529da9625+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_b340826080c529da9625+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_b340826080c529da9625+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_b340826080c529da9625+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..9d283f5da346ad50b0247532c91261aacc012710
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_b340826080c529da9625+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41410f822eeb3adda775b710ce6765632f8b8c31d397fd0f2bece758f6c3a88f
+size 54883
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_b340826080c529da9625+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_b340826080c529da9625+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..a8604404b762f4592d1dd1e10589f6a882239656
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_b340826080c529da9625+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_bc4eef25d6686ad21908+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_bc4eef25d6686ad21908+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_bc4eef25d6686ad21908+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_bc4eef25d6686ad21908+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_bc4eef25d6686ad21908+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_bc4eef25d6686ad21908+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_bc4eef25d6686ad21908+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..fd0a82cfe33b0c67c2da7042ea078fd07b9af254
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_bc4eef25d6686ad21908+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d69d666c8e79bcd979378af3256d6c6d15cb8493f366300361649a5e3dd9090
+size 368279
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_bc4eef25d6686ad21908+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_bc4eef25d6686ad21908+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..a8fc8840456eb867ef8d430073f904b3a56b1170
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_bc4eef25d6686ad21908+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9118172019540d9ca1bbc02dc57e92255ad1abd2bbf979c25c1e59cc4e041ae
+size 13569024
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_bdab92f819266df89445+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_bdab92f819266df89445+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_bdab92f819266df89445+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_bdab92f819266df89445+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_bdab92f819266df89445+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_bdab92f819266df89445+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_bdab92f819266df89445+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..9a9b82e2c7f140ecaff3fb539a3d96794a71ffb2
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_bdab92f819266df89445+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00485322960944078f78d529e12539c937a64673cccdbf14d8353f757d7a9d5d
+size 253236
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_bdab92f819266df89445+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_bdab92f819266df89445+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..5dafbf42d826dd367203f4743ebe3561b988b7bd
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_bdab92f819266df89445+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a59dc813b313ff41671890ca15546aab73fd2876cc02a40afedadf9e7403506
+size 3544064
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..5fb482a53467527a6889a8d83a818400bd6344d4
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c492ac98b1d0a269548601584cf6326108d3f717531f11a041838a223978cc
+size 131287
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..dd219a59ca826cec3ef5f6b05ce06a06064fd2e9
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..5fb482a53467527a6889a8d83a818400bd6344d4
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c492ac98b1d0a269548601584cf6326108d3f717531f11a041838a223978cc
+size 131287
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..6045193291507a8541d4799bd0c57916ac7f2ab1
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_c9efa4ab290c9084e21b+7ac4dbae/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_cb3ec814cbdbd1a9df1b+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cb3ec814cbdbd1a9df1b+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cb3ec814cbdbd1a9df1b+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_cb3ec814cbdbd1a9df1b+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cb3ec814cbdbd1a9df1b+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_cb3ec814cbdbd1a9df1b+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cb3ec814cbdbd1a9df1b+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..6a51d9a4adfd88c9faf40e95573805dbdb84a3f0
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cb3ec814cbdbd1a9df1b+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:685f2e99680c4bdff3b8b6a2944f15f8cfa60ab4d3e373d5f2197333a9d3a100
+size 256787
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_cb3ec814cbdbd1a9df1b+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cb3ec814cbdbd1a9df1b+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..41d2d60d589e36cd03c4f01fac4c9852e2e7296e
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cb3ec814cbdbd1a9df1b+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4185f940bcaf26285b6463618da2d27060358ceff8eb81b2d08b42e80c2428c9
+size 12534784
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_cba1f822eae6e36bec23+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cba1f822eae6e36bec23+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cba1f822eae6e36bec23+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_cba1f822eae6e36bec23+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cba1f822eae6e36bec23+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_cba1f822eae6e36bec23+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cba1f822eae6e36bec23+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..dc75003ab238655dcfa04b8076285198f6e07aaa
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cba1f822eae6e36bec23+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b4da838abd9f8f4b18c4f39f37c909db8f1edd24a48c29dc5283a90a659ce63
+size 32359
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_cba1f822eae6e36bec23+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cba1f822eae6e36bec23+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..aa3abfafc351b3b8b24a01ba472cc78a410c5fcd
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cba1f822eae6e36bec23+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_cc3209876d863b607d80+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cc3209876d863b607d80+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cc3209876d863b607d80+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_cc3209876d863b607d80+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cc3209876d863b607d80+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_cc3209876d863b607d80+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cc3209876d863b607d80+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..a6fa74fa8bc547bae72eb3a0ec445222d5924b14
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cc3209876d863b607d80+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad9e7cebf45aa012836ca8561e6ee0065f3ad6e4e3c3fd01cdf0e7833ce6108
+size 22842
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_cc3209876d863b607d80+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cc3209876d863b607d80+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..227d35d5ea47263ffdc02bd3c2711660317dface
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_cc3209876d863b607d80+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3a23d6ec050af87eae9+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3a23d6ec050af87eae9+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3a23d6ec050af87eae9+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3a23d6ec050af87eae9+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3a23d6ec050af87eae9+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3a23d6ec050af87eae9+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3a23d6ec050af87eae9+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..7a51e1bca27071d9c61c54f5ca61c4396f1a411c
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3a23d6ec050af87eae9+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b708dde4116c9c13fd484c15ffcfecf4e5a4dc698242f7fc7c4045841e96a03
+size 30279
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3a23d6ec050af87eae9+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3a23d6ec050af87eae9+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..cb3a1457076949a8a82efafab7b6ac2233994f2a
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3a23d6ec050af87eae9+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3aaf1a76bba7180be81+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3aaf1a76bba7180be81+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3aaf1a76bba7180be81+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3aaf1a76bba7180be81+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3aaf1a76bba7180be81+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3aaf1a76bba7180be81+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3aaf1a76bba7180be81+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..82742b0c3e0f47c4c42db41206a11d8a49c3b792
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3aaf1a76bba7180be81+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47bdc2e82126d171a82a921451b674da99f11253028572f2a7c48fde48a4446d
+size 70244
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3aaf1a76bba7180be81+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3aaf1a76bba7180be81+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..7b961ee44e34bd75ebbfbb3b3701fb3b0ec13369
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d3aaf1a76bba7180be81+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_d9b9d6ea0afd6ef5be19+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d9b9d6ea0afd6ef5be19+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d9b9d6ea0afd6ef5be19+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_d9b9d6ea0afd6ef5be19+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d9b9d6ea0afd6ef5be19+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_d9b9d6ea0afd6ef5be19+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d9b9d6ea0afd6ef5be19+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..73d2db9a6fff5abfa68712abf468d46d1fa50617
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d9b9d6ea0afd6ef5be19+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ddb6ce8ad4d9b03640c2fb9cafa9dc7abdf8793b1aa7efd99be577b1640038
+size 32022
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_d9b9d6ea0afd6ef5be19+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d9b9d6ea0afd6ef5be19+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..ebf7c65677f8513f2c29d03f925ed6435a7b4209
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_d9b9d6ea0afd6ef5be19+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_dade954b475a132a2c70+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_dade954b475a132a2c70+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_dade954b475a132a2c70+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_dade954b475a132a2c70+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_dade954b475a132a2c70+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_dade954b475a132a2c70+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_dade954b475a132a2c70+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..7cff5af8697165587ebc5b5c359a94e1786ecfc0
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_dade954b475a132a2c70+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9efbe4fb0b022608b85e9d082712c1fc06de024558f98fc430971ea3eaf7cac4
+size 23190
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_dade954b475a132a2c70+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_dade954b475a132a2c70+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..edd20ccd9023ac0d823e0da463778acc43e17217
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_dade954b475a132a2c70+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_dca9330871e128038c15+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_dca9330871e128038c15+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_dca9330871e128038c15+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_dca9330871e128038c15+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_dca9330871e128038c15+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_dca9330871e128038c15+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_dca9330871e128038c15+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..7d4124c5fa1284cba5cb843fa43c71a7c5caf4a8
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_dca9330871e128038c15+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2777e17700878245eb5031067f4e08821dd18cf17fec3fa97e5c822ea66d32
+size 21272
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_dca9330871e128038c15+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_dca9330871e128038c15+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..d63fad20d506f74fa96cd0860c89379ae5c21fb9
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_dca9330871e128038c15+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ddff44ee1a9acf0b9d1c+8a3305d3/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ddff44ee1a9acf0b9d1c+8a3305d3/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..2b12c328588df6955322fd03473d7e93dc523be6
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ddff44ee1a9acf0b9d1c+8a3305d3/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=5"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ddff44ee1a9acf0b9d1c+8a3305d3/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ddff44ee1a9acf0b9d1c+8a3305d3/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ddff44ee1a9acf0b9d1c+8a3305d3/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ddff44ee1a9acf0b9d1c+8a3305d3/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..c276e80a94a3057f6e2bb23e901f548386ce2cc3
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ddff44ee1a9acf0b9d1c+8a3305d3/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df82520441eda9ae1dfabaacf9b201d8cb88417056bc5d4168d4931f9f3618e3
+size 9259
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ddff44ee1a9acf0b9d1c+8a3305d3/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ddff44ee1a9acf0b9d1c+8a3305d3/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..f2652447d39005a382df87013e2d6081feda8c41
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ddff44ee1a9acf0b9d1c+8a3305d3/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_e1e1e3a85cd7a83e0dd1+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e1e1e3a85cd7a83e0dd1+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e1e1e3a85cd7a83e0dd1+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_e1e1e3a85cd7a83e0dd1+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e1e1e3a85cd7a83e0dd1+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_e1e1e3a85cd7a83e0dd1+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e1e1e3a85cd7a83e0dd1+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..ab3bd839fef37c4a3b5a8bf868f8fe35f02cb807
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e1e1e3a85cd7a83e0dd1+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef586749c16d7cba7e77cd53329eeeb9aba32259406e923c890c27471b2c8293
+size 331842
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_e1e1e3a85cd7a83e0dd1+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e1e1e3a85cd7a83e0dd1+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..ac04193c560e52724bbaca3251f89dc71e625285
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e1e1e3a85cd7a83e0dd1+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54870b4b0f12ab715d5d45382b85164bfe5882686a44f7f0a26987feca6798f2
+size 3113984
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_e4392d66f75196016d72+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e4392d66f75196016d72+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e4392d66f75196016d72+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_e4392d66f75196016d72+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e4392d66f75196016d72+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_e4392d66f75196016d72+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e4392d66f75196016d72+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..66626acd9f2364a1248793bd6f72a92089c4b28e
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e4392d66f75196016d72+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:444876f94c944300a1c1d4cc11271f8766ee312b0be0f4de8fd52398a45b9e4d
+size 22270
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_e4392d66f75196016d72+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e4392d66f75196016d72+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..69091d5fd37e27c90e773e756d441cbf50c096dc
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e4392d66f75196016d72+613edded/model.neff differ
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_e503bb548c30caa02b1a+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e503bb548c30caa02b1a+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e503bb548c30caa02b1a+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_e503bb548c30caa02b1a+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e503bb548c30caa02b1a+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_e503bb548c30caa02b1a+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e503bb548c30caa02b1a+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..2068cca602004a40cf5c388a1f23dda03fda1a0a
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e503bb548c30caa02b1a+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc3d270c2fbbfeb0a1d7916912628f018284cffe9b8dce116b87890e1ef9664
+size 256787
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_e503bb548c30caa02b1a+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e503bb548c30caa02b1a+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..e1d9056117ebb88d08e6456c82d8961630077133
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_e503bb548c30caa02b1a+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe817ab369c3c1da6138eb604b81c4911d69f52d936a84a6f67f1de8d325ee3
+size 6523904
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ea4f2290b2fcba35e5fb+7ac4dbae/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ea4f2290b2fcba35e5fb+7ac4dbae/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..693bde3363db2a11cb33168104c3818e63f73284
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ea4f2290b2fcba35e5fb+7ac4dbae/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn2", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ea4f2290b2fcba35e5fb+7ac4dbae/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ea4f2290b2fcba35e5fb+7ac4dbae/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ea4f2290b2fcba35e5fb+7ac4dbae/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ea4f2290b2fcba35e5fb+7ac4dbae/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..bc9bc8ac7693b689926a6a00afd479a3272979f6
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ea4f2290b2fcba35e5fb+7ac4dbae/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de5313a75cbe6e27a8eb30e19f95cdb280e16af6db1df3f0d60e11cd31f9ff20
+size 302383
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ea4f2290b2fcba35e5fb+7ac4dbae/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ea4f2290b2fcba35e5fb+7ac4dbae/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..381fe836d183909792f1575fe2915ab1da5fddd0
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ea4f2290b2fcba35e5fb+7ac4dbae/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:511eb87c0fb3b4ef35e03893ceb1ec298bbf63ac3588e4f92e35efdcec4c3720
+size 6482944
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ff6455a3b7d2ec8e1f2d+613edded/compile_flags.json b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ff6455a3b7d2ec8e1f2d+613edded/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ff6455a3b7d2ec8e1f2d+613edded/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
\ No newline at end of file
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ff6455a3b7d2ec8e1f2d+613edded/model.done b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ff6455a3b7d2ec8e1f2d+613edded/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ff6455a3b7d2ec8e1f2d+613edded/model.hlo_module.pb b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ff6455a3b7d2ec8e1f2d+613edded/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..65bd2a1c2cc299b870e33eeacb7196c0ef175fc4
--- /dev/null
+++ b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ff6455a3b7d2ec8e1f2d+613edded/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c5ccd5b5df9ab2c908399fda343ea0addaaee013249f6c4d9abdba214731486
+size 57978
diff --git a/neuronxcc-2.16.303.0+d9f03cda/MODULE_ff6455a3b7d2ec8e1f2d+613edded/model.neff b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ff6455a3b7d2ec8e1f2d+613edded/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..7c1d79598eeec28a49930cd3407569f1f32e024d
Binary files /dev/null and b/neuronxcc-2.16.303.0+d9f03cda/MODULE_ff6455a3b7d2ec8e1f2d+613edded/model.neff differ