Synchronizing local compiler cache.

.gitattributes

@@ -12215,3 +12215,5 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_a104e1d968fe30c4ac21+ca355898/wrapped_nef
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_050801613474e5a8dafe+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_887a24107396c649d6c0+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_887a24107396c649d6c0+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_082293dad00be4d3c3fc+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_082293dad00be4d3c3fc+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.18209.0+043b1bf7/MODULE_082293dad00be4d3c3fc+ca355898/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_082293dad00be4d3c3fc+ca355898/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1028849e83cf491d3dba614c6f80394150d911a91d5aea12afb950177f59f0
+size 2072225

neuronxcc-2.21.18209.0+043b1bf7/MODULE_082293dad00be4d3c3fc+ca355898/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d64f50f82a3ae35f8f20a5eabd4e443da981f2226dfe2e750943389667b4b6
+size 799744

neuronxcc-2.21.18209.0+043b1bf7/MODULE_082293dad00be4d3c3fc+ca355898/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90302f6427b3860d6f350b0983b9c5aa7df8df99d71e5eb6de39bc473430b1df
+size 1073005

neuronxcc-2.21.18209.0+043b1bf7/MODULE_887a24107396c649d6c0+0b01cb42/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_887a24107396c649d6c0+0b01cb42/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cff9bbd09783c80111230c07d2efac680aaae1a2c61f3ee64f62b8bb097d6ec0
+size 1667462

neuronxcc-2.21.18209.0+043b1bf7/MODULE_da7775df79bbce55f4dc+c2248236/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_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_da7775df79bbce55f4dc+c2248236/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69830c3dd3b2bebf9180892ad4a6a0f0a885202bc5a8d42e020311e1fcffc534
+size 33836606

neuronxcc-2.21.18209.0+043b1bf7/MODULE_da7775df79bbce55f4dc+c2248236/model.log

@@ -0,0 +1,3 @@
+Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/context_encoding_model/_tp0_bk0/model.MODULE_da7775df79bbce55f4dc+c2248236.hlo_module.pb', '--output', '/tmp/nxd_model/context_encoding_model/_tp0_bk0/model.MODULE_da7775df79bbce55f4dc+c2248236.neff', '--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_model/_tp0_bk0/log-neuron-cc.txt', '--verbose=35']: [XCG815]  Estimated peak HBM usage (23.148GB) exceeds 16GB. Neff might be unable to load on chip. If you believe this estimation to be inaccurate, you can disable the check using: `--internal-backend-options=' --disable-hbm-usage-check '` - 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.
+2025-10-21T15:42:14Z Non-signal exit. Backend exited with code 1 and stderr: [XCG815]  Estimated peak HBM usage (23.148GB) exceeds 16GB. Neff might be unable to load on chip. If you believe this estimation to be inaccurate, you can disable the check using: `--internal-backend-options=' --disable-hbm-usage-check '` - 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.
+