diff --git a/.gitattributes b/.gitattributes
index 6a8f574341ca87d1f9767daf1b5197fb8a3c8508..3fd462af6e4aa6137db7bdec9ffbdf49f21d2613 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -7082,3 +7082,30 @@ neuronxcc-2.21.33363.0+82129205/MODULE_9a1b9a8b43d1665adae5+a02c3a36/model.neff
 neuronxcc-2.21.33363.0+82129205/MODULE_9a1b9a8b43d1665adae5+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_eb5005f121a849e69eb7+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_eb5005f121a849e69eb7+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_13ceff346d0e3479704a+6e4949b4/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_5ad2d5f306d13c506440+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_826bbed76f9f977f94c0+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_84656e81eaefaaeb593f+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_c75fd5e63a178ce4f3d1+677eeb9d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_cd398d15ddca2b8db9a9+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_e337acd66701db458735+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_ef93001ee65461791427+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_f33d66622d796b2877aa+283df001/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_fa29fc69337939622d95+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_fb598b8eba6e5a92e75f+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..19c16cfc86a6f1d72b1fe130742a1de40c66e10a
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aede2c8d2d65ee80658dcddb37304acb08ec589dbb2707962c654478719d7fd
+size 904137
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..005cd09a4effa1e19f38cbd37316cdaf53cdfc79
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82cfc3dfcdb273c5075fd53c7cf5a1969e63dbeecdcd045794264fde9742392c
+size 4998144
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/wrapped_neff.hlo
new file mode 100644
index 0000000000000000000000000000000000000000..c96dfb52d1a0e3f3f832894cb90d003637ed7431
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0680112a1970faff8f3a+a02c3a36/wrapped_neff.hlo
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a58280421d3ed9a1e0893521b9dfa1c92a6db24cd230c60c0687bfefc18e04c
+size 5164668
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..717d36ea4a225299bdf0d0646c14ae0f158981f1
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a649ed18d8cf22148cf1727477a6e0cee892573790834d9455503d83038ec7
+size 85208
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..afcec2dd0eb4063ac5dd28f4b2f1e21783d25470
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546630b25a8444602e63c1aea3a8363e60f2c8c09e9681284c833f6e05eb395d
+size 257024
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/wrapped_neff.hlo
new file mode 100644
index 0000000000000000000000000000000000000000..463c09c2ea6fe1c3d86c4a02dfc5702fd71b47ef
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0a1bf3b6e86f854781c2+a02c3a36/wrapped_neff.hlo
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e826c53104b3589c79de96bde775712a147396c7b4b681ed3453a7227629ba
+size 265207
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..99428203f594a84d1ee466e0f301526cf8f42f73
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194247f6c266078d61032d45dc11cfdc31dcce5959d33c6337fa7d27454171da
+size 87126
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..5c0ffc1a4112e38961156e7522ea00898cee93e5
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b94924e9a5902f3716cb75da310be67a1a3c4f14f2c1dbfb7999fdfe0f1dadee
+size 287744
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/wrapped_neff.hlo
new file mode 100644
index 0000000000000000000000000000000000000000..3dc8a3ae418dfc53b4ba9c08ab266cfe13f577c4
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_131d6c7c245c7131bd76+a02c3a36/wrapped_neff.hlo
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7489edb28de75b5a233411b7723a46e902615262b35c0ac6ac9887eec09236d
+size 295957
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_13ceff346d0e3479704a+6e4949b4/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_13ceff346d0e3479704a+6e4949b4/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..2ad69cd01383a682715fed6c7faaf92a72533ca6
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_13ceff346d0e3479704a+6e4949b4/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_13ceff346d0e3479704a+6e4949b4/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_13ceff346d0e3479704a+6e4949b4/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_13ceff346d0e3479704a+6e4949b4/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_13ceff346d0e3479704a+6e4949b4/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..9dfa4b248bf7c86f476d45bc072d65d054c81302
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_13ceff346d0e3479704a+6e4949b4/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c235fd154884dae0bb0408b3066c676d3279b38350a7637b8a4248b6691c936f
+size 84807
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_13ceff346d0e3479704a+6e4949b4/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_13ceff346d0e3479704a+6e4949b4/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..f83f5aad0ddf31f8ee67358ed0be55d0bfff2566
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_13ceff346d0e3479704a+6e4949b4/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b906ddbae4fb13528dc91ceda5cb21c3da0d86586f0cf463ec33be1141dcd2
+size 646144
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_47c06cec950237374a0e+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_47c06cec950237374a0e+a02c3a36/model.neff
index cc8bc358589475a92ec2b8d040e4d7ee5c27bb64..132e3ad43249b32c2e73121da32f745168f5f481 100644
--- a/neuronxcc-2.21.33363.0+82129205/MODULE_47c06cec950237374a0e+a02c3a36/model.neff
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_47c06cec950237374a0e+a02c3a36/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca1595984e251c12aabf75adbd8edf823c9b992e9e9c96ae7a3f3e2bbc25de2
+oid sha256:10cf0d8e6b6f0b09c9759911af6482a82df2f590f6394c3ebf7e274704c63274
 size 287744
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_47c06cec950237374a0e+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_47c06cec950237374a0e+a02c3a36/wrapped_neff.hlo
index c5ace886144eef885f0ffac3e31fa7fb8b22b243..63ded5b190bce02a50395edf7242aada72e1eca4 100644
--- a/neuronxcc-2.21.33363.0+82129205/MODULE_47c06cec950237374a0e+a02c3a36/wrapped_neff.hlo
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_47c06cec950237374a0e+a02c3a36/wrapped_neff.hlo
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c71914ebc3aeef62dfc9a83c5f4182bc4e30e670d11b40afafed4fe96796536
+oid sha256:83869159f0d69e24395c4ca4c8ead35c5600e4a26de86d06e5424156fbaa0353
 size 295957
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..8d0e1832f36371c947458374734b53549fa617bc
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4fd29746283c3bf9e8a296c0a0c1a4aba33eef54f20dd7eed545f4dff63e335
+size 680975
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..5f39bf0019b5d6c11fe25d2bcc44309f8d573485
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb4395f507db8e19479ec3f9af8984ef0ed77b7d702202468b3634faf02f67a
+size 543744
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/wrapped_neff.hlo
new file mode 100644
index 0000000000000000000000000000000000000000..2309d403dbc2b9397870779f4e6c659d86826696
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4da1b782d99a7304f0e2+a02c3a36/wrapped_neff.hlo
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a764fed6315873da19c5fe7a67ef0ba9527e6597d0dc04c2829e2f32f8a0594c
+size 563245
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5ad2d5f306d13c506440+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_5ad2d5f306d13c506440+24129607/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5ad2d5f306d13c506440+24129607/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5ad2d5f306d13c506440+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_5ad2d5f306d13c506440+24129607/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5ad2d5f306d13c506440+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_5ad2d5f306d13c506440+24129607/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..8d6fa80089c130a6372bef6c30adb443327ef40d
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5ad2d5f306d13c506440+24129607/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546055e83ecab4869934d006e22de9b0749a7ba92647736a2fd3717385302934
+size 81516
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5ad2d5f306d13c506440+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5ad2d5f306d13c506440+24129607/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..1743386812db96c1985d42ca2a640fc29f489ec2
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5ad2d5f306d13c506440+24129607/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f30a96faa2c3d7d53564b4faa524529849c0bafebb2a7cd2a2d3565199b4afab
+size 267264
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..8441d02f09fde5e8d54ee7cd9e8a2f94997042a3
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ddfc4058c88c14f1f3999a3f3aa5c3fb167e3eff80a639290325506909c6b2f
+size 95557
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b850e04ea7ac2f8c86c905152a36d73edb4ad162
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386711bc7e3781a301911fef0d205883713fcc35449c319fae73e7fc0dee9ce4
+size 277504
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/wrapped_neff.hlo
new file mode 100644
index 0000000000000000000000000000000000000000..7716bcd00894211b0f8aa6aebd1ec5f982f43be9
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6ed16792f2699fac18e0+a02c3a36/wrapped_neff.hlo
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d018e14fafeaea830330e04210880e735034466d75b6f8afb853aaa10e8828d
+size 288898
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_78ef14a5e66efce40c70+2dde74c7/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_78ef14a5e66efce40c70+2dde74c7/model.hlo_module.pb
index b2d86ede422be003223376919aeba1b14b253ecd..8c89a0fe3bb68fde36fb6e7b7289304585e2b0a1 100644
--- a/neuronxcc-2.21.33363.0+82129205/MODULE_78ef14a5e66efce40c70+2dde74c7/model.hlo_module.pb
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_78ef14a5e66efce40c70+2dde74c7/model.hlo_module.pb
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a727f0ba6420e2e1182136fcff0af6b605200f6350b2998fecd4c79dc080fa54
+oid sha256:9b99ecac1d2fba0ada5643f1cdf386f9d8501ebe4ed6c14f367a826c19efce49
 size 92677
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_78ef14a5e66efce40c70+2dde74c7/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_78ef14a5e66efce40c70+2dde74c7/model.neff
index 11d95918b49990a0d1cdf7a88346d8f59b86c96c..e0cf2c4a68422a7a924e641b9a049a1159d86fab 100644
--- a/neuronxcc-2.21.33363.0+82129205/MODULE_78ef14a5e66efce40c70+2dde74c7/model.neff
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_78ef14a5e66efce40c70+2dde74c7/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e435caa65bc42ea254fe7e485b1c0ba866a28e9c16cfc31b1857fc5cebad0d
+oid sha256:5c4be434d2ef7d79586a1f957fdaa1048bfdc869de59c03b5b2a87826f7806ea
 size 369664
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_78ef14a5e66efce40c70+2dde74c7/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_78ef14a5e66efce40c70+2dde74c7/wrapped_neff.hlo
index f9891845ff20f94c61f1b3348e434dcb59f56096..8aeca084c40ce9870a875d47ab518cddfda21657 100644
--- a/neuronxcc-2.21.33363.0+82129205/MODULE_78ef14a5e66efce40c70+2dde74c7/wrapped_neff.hlo
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_78ef14a5e66efce40c70+2dde74c7/wrapped_neff.hlo
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba6a5e7fb172575522d0ee597ae759d5d51ff44b387382c3119d0ff015c31655
+oid sha256:a47c16359d170b75e756c9f1f95b3331b4c6b52d8b6d628f039725d14acbe3ba
 size 379225
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_826bbed76f9f977f94c0+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_826bbed76f9f977f94c0+24129607/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_826bbed76f9f977f94c0+24129607/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_826bbed76f9f977f94c0+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_826bbed76f9f977f94c0+24129607/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_826bbed76f9f977f94c0+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_826bbed76f9f977f94c0+24129607/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..82b08d5da7d400509d623760df8cfc407b2ca577
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_826bbed76f9f977f94c0+24129607/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebdbd2f771cf3c318754304a5f5f110207bf5f7735e07a5254607e3abca36f63
+size 79552
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_826bbed76f9f977f94c0+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_826bbed76f9f977f94c0+24129607/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b8163ceb503f28d31b508e4263924118ba117f72
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_826bbed76f9f977f94c0+24129607/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe59a5f39ca2b14c71aabb12a156bf84eb6bf1b914abd12026ba8db1de52315f
+size 338944
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_84656e81eaefaaeb593f+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_84656e81eaefaaeb593f+24129607/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_84656e81eaefaaeb593f+24129607/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_84656e81eaefaaeb593f+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_84656e81eaefaaeb593f+24129607/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_84656e81eaefaaeb593f+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_84656e81eaefaaeb593f+24129607/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..6e81e985cdadd827f927a352ef6c7c27a9e24f6b
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_84656e81eaefaaeb593f+24129607/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:226520757a94ced9214c615bc2496045526dab8114f2ab79beb78c7b064930a9
+size 694128
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_84656e81eaefaaeb593f+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_84656e81eaefaaeb593f+24129607/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..319c4bf390c3a1ac817681965edbb43a5b6ec79a
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_84656e81eaefaaeb593f+24129607/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb89ba7755fc74f16da3c26c1219d52f5266f08f97e876517318fe8314a213c
+size 625664
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..3d7d85cd3d975162683053faa369dcc6259604af
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d3f8d82d6f45827207e27bc89760cea90909c
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25d19f95bd2d2d22716d50dd7ff25b13a26b0bd88df29dca923442e3a52de242
+size 74684
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..3a1829605302fdb9da4ca4e86c66bf09f359ae4b
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede9d4f2677bed7427f874e5f503791ef1cc8be4af7d4e6bd1a7aa6bb9ee467d
+size 277504
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/wrapped_neff.hlo
new file mode 100644
index 0000000000000000000000000000000000000000..f18cf246f89228d80f42a35b5d855f2109134a05
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b651bd725ae2d8726217+80d05c3f/wrapped_neff.hlo
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac4db0e4cb996e91e41b41f3e9aaf8204fb1bbd888dc69bb4606c019bf83fdc
+size 289434
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..bcff2cce1144329bac7c6cb34cdcaabd69311e8a
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22087adc7a012a994ce8911f4eda9a541258e32cbea09a62369de2492d056ab8
+size 405481
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..2db58043032e46a9ff844aed4b060e91282dca63
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f81c3f224e8d6a6d6143de80e7fee956d55148d61f7ba601bf225dfaea01a0
+size 1997824
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/wrapped_neff.hlo
new file mode 100644
index 0000000000000000000000000000000000000000..4ad774f6b1be8a69e605a360eb0490ea4502e49d
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b87961c02022113d30f4+a02c3a36/wrapped_neff.hlo
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:767dccde03e8e5cfbfdabc2ad4c4a7e35b803036f5df49dee8b0e106aca1a752
+size 2090737
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..3467a28f4d54fb66e965ba13a331395f7be50279
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea4e9cc13ab00a8e2e6f922b982507ed418e56b8f1b5c6c8e3d72c9dfdd8d44
+size 574388
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..16b067f0e2339bcb9dec283c5994380923e5dc9a
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32525c928c868fca4bff354f75d0607cbe9c470aaafaba8e34a9da5a37cf8ba
+size 1086464
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/wrapped_neff.hlo
new file mode 100644
index 0000000000000000000000000000000000000000..bb463f6d6686c4cee216899638237371322ff207
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c6ac9f1b555d05bd7e39+a02c3a36/wrapped_neff.hlo
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3f91118d993e6dceb74b20a7733d83daf3b5589cca7da9638151b8a6efb76a
+size 1208853
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c75fd5e63a178ce4f3d1+677eeb9d/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_c75fd5e63a178ce4f3d1+677eeb9d/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..ae7e0c6790082c43cd145aae8cc7e3cc89e15ca8
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c75fd5e63a178ce4f3d1+677eeb9d/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/speculation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c75fd5e63a178ce4f3d1+677eeb9d/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_c75fd5e63a178ce4f3d1+677eeb9d/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c75fd5e63a178ce4f3d1+677eeb9d/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_c75fd5e63a178ce4f3d1+677eeb9d/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..75e0d55ae0c6061c1e8b08f4f2195fa17f80e49a
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c75fd5e63a178ce4f3d1+677eeb9d/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed708e361a873a0f5a0f54a37a60ceaefda28896ee334ed372676c770f162697
+size 455594
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c75fd5e63a178ce4f3d1+677eeb9d/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_c75fd5e63a178ce4f3d1+677eeb9d/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..9b891c7aadd149e5d575bce29ab60584948cfb40
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c75fd5e63a178ce4f3d1+677eeb9d/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18051bbe5941a0521ceed1401548d145062cc95c2f1bb7a9c886e052cbf7a121
+size 3922944
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cd398d15ddca2b8db9a9+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_cd398d15ddca2b8db9a9+24129607/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cd398d15ddca2b8db9a9+24129607/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cd398d15ddca2b8db9a9+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_cd398d15ddca2b8db9a9+24129607/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cd398d15ddca2b8db9a9+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_cd398d15ddca2b8db9a9+24129607/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..6e4701bc0c10a25a0a06cba3aaa67a9a5f6e4d7b
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cd398d15ddca2b8db9a9+24129607/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ada1a8cdd1e2563985ad4f6b5da6f07dfb3891689064800b5ae54f325d71200
+size 83504
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cd398d15ddca2b8db9a9+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_cd398d15ddca2b8db9a9+24129607/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..abc83a2b1cd62217075810c4627fb6d1e190f44a
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cd398d15ddca2b8db9a9+24129607/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5149332130fc9012cb373e61bd59cf414015efae208f0432a94f8067650f33e
+size 328704
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e337acd66701db458735+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_e337acd66701db458735+24129607/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e337acd66701db458735+24129607/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e337acd66701db458735+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_e337acd66701db458735+24129607/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e337acd66701db458735+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_e337acd66701db458735+24129607/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..fe83deb92860f016e77e8058cfa8ef9da53dd57c
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e337acd66701db458735+24129607/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8577f49ec00439c40e1058ddef82ca8a142655c3cc99be5bdd45d4a97b4ec763
+size 532500
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e337acd66701db458735+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_e337acd66701db458735+24129607/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..1ee3e0bb830c12d9f8f7eee399942590125b4d95
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e337acd66701db458735+24129607/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043a5ae6643a58a7ff6a5bf07db42c29e3482ade0f0b523dd5b4151f3413cfdd
+size 1813504
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ef93001ee65461791427+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ef93001ee65461791427+24129607/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ef93001ee65461791427+24129607/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ef93001ee65461791427+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ef93001ee65461791427+24129607/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ef93001ee65461791427+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ef93001ee65461791427+24129607/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..0b3c8f147b8bac5783832babfa2b8dbc7477e6be
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ef93001ee65461791427+24129607/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9f6cc64dd38c523fa33828cc0cca5eb3e0edb9c47024b7f6c748e59c22cb54
+size 82772
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ef93001ee65461791427+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ef93001ee65461791427+24129607/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..9bb814d32491348c038ac36048cba43b28ac2a5b
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ef93001ee65461791427+24129607/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f6e5ccf3b0e4969397c1b114409aa2e1cd46189425201864551b0b64a89b19
+size 267264
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f33d66622d796b2877aa+283df001/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_f33d66622d796b2877aa+283df001/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..58fbf6b9366d9e28d7f19321e85acd4cd96c0614
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f33d66622d796b2877aa+283df001/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f33d66622d796b2877aa+283df001/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_f33d66622d796b2877aa+283df001/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f33d66622d796b2877aa+283df001/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_f33d66622d796b2877aa+283df001/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..999c3d79c7a98a57ce36d6cf123c7b54ad0588b1
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f33d66622d796b2877aa+283df001/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335c133575936870fb0fae94881672481e07292ccd05798a21f93552aef3b7fd
+size 97794
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f33d66622d796b2877aa+283df001/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_f33d66622d796b2877aa+283df001/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..826509d6eb373a6ed7f50bb84e2358525d9f7443
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f33d66622d796b2877aa+283df001/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd0c5e8dcc29d47f0b544761ad02481e325f7bc70226ed229787ae27520b274
+size 410624
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fa29fc69337939622d95+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_fa29fc69337939622d95+24129607/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fa29fc69337939622d95+24129607/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fa29fc69337939622d95+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_fa29fc69337939622d95+24129607/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fa29fc69337939622d95+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_fa29fc69337939622d95+24129607/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..7fb4c9bbc41a898533b0531c218b32b9039aa882
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fa29fc69337939622d95+24129607/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5758f104aa59185e2d260ad19edb597a812c714aa81dc87048736add612f9418
+size 90382
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fa29fc69337939622d95+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_fa29fc69337939622d95+24129607/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..99d6d6953d3fa39fe7e0a14b49b5eee452c54cfb
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fa29fc69337939622d95+24129607/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40efb18e323706a3b13f75af55a66201e078f38c2ed010d562521d6f9812aa7e
+size 359424
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fb598b8eba6e5a92e75f+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_fb598b8eba6e5a92e75f+24129607/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fb598b8eba6e5a92e75f+24129607/compile_flags.json
@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
\ No newline at end of file
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fb598b8eba6e5a92e75f+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_fb598b8eba6e5a92e75f+24129607/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fb598b8eba6e5a92e75f+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_fb598b8eba6e5a92e75f+24129607/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..063bbf04ebf17e3e2c055b77dc1fd871e19ac9b6
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fb598b8eba6e5a92e75f+24129607/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a447ade2a2d2fbae6cb8aba2246b5ec0bf2861cbf08f1ed4c1bf22b7625db059
+size 761066
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fb598b8eba6e5a92e75f+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_fb598b8eba6e5a92e75f+24129607/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..92b18666ed672f0ab53eb50254d30de327134b35
--- /dev/null
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fb598b8eba6e5a92e75f+24129607/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1577e7107e5832f9db26e7a3f4aa9c24355fb28f03595c396a8ebcf1283bd46
+size 12493824
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fe6b8b40a8e1d622e71e+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_fe6b8b40a8e1d622e71e+a02c3a36/model.hlo_module.pb
index 1506bd2e25ca3c180a9d2261b6abebf087eafd48..90b29d24d1deec0ccffe07084324f7b6bc10d4f4 100644
--- a/neuronxcc-2.21.33363.0+82129205/MODULE_fe6b8b40a8e1d622e71e+a02c3a36/model.hlo_module.pb
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fe6b8b40a8e1d622e71e+a02c3a36/model.hlo_module.pb
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7831067a571b1988d3d3f814b6b7baf2e8023f98dc91a6a398eec042943e06a
+oid sha256:7bca3bd92e92ac125defbadf7e843c65755895cb44e5cdcbc92712a880e49ab1
 size 84493
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fe6b8b40a8e1d622e71e+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_fe6b8b40a8e1d622e71e+a02c3a36/model.neff
index e7ccfb79b797dbfff7c1cad4d432574e32ca946e..5c2f0da8a8b70ab020f0d59a673754c2042e775d 100644
--- a/neuronxcc-2.21.33363.0+82129205/MODULE_fe6b8b40a8e1d622e71e+a02c3a36/model.neff
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fe6b8b40a8e1d622e71e+a02c3a36/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e84f7b890583ca31af1b8bc421ba30d1d2f845ac80c2371c8aa28f52eb93998
+oid sha256:3aced29a9eab1a81387206b2a9a5f5a3716aafec360b3350f677fd860cb5d8a5
 size 216064
diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fe6b8b40a8e1d622e71e+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_fe6b8b40a8e1d622e71e+a02c3a36/wrapped_neff.hlo
index cfa3519b2b9d5f69f8239173f888ca3aef9bdeba..8f8c5600163c84a747bde4c53e4cf27eeaa69539 100644
--- a/neuronxcc-2.21.33363.0+82129205/MODULE_fe6b8b40a8e1d622e71e+a02c3a36/wrapped_neff.hlo
+++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fe6b8b40a8e1d622e71e+a02c3a36/wrapped_neff.hlo
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d636b6604e0f586069efbc0ce6723b497855c162a9a68aa017e38f1c54daf98e
+oid sha256:539c539df8ca90271f687afdf1aa3a80a65aa6dedea21b0bfd01eadbac362261
 size 224275