Synchronizing local compiler cache.

.gitattributes

@@ -9923,3 +9923,7 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_054cfe09cdfc1f32d0d3+431f5505/model.neff f
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_3c71a838fcbfa1bfff33+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_6104e0178f4c97e10ec1+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_6104e0178f4c97e10ec1+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_20949b5f2d7f8f08fcb7+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_41a325511679b7ebebbb+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_981fee31185da34ed5e1+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_981fee31185da34ed5e1+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.19.8089.0+8ab9f450/MODULE_20949b5f2d7f8f08fcb7+431f5505/compile_flags.json

@@ -0,0 +1 @@
+"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"

neuronxcc-2.19.8089.0+8ab9f450/MODULE_20949b5f2d7f8f08fcb7+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec894632e547f5df4f2c8e964aa89e83e52d1ff786c0e9321adf6f5ae22cc7c
+size 511796

neuronxcc-2.19.8089.0+8ab9f450/MODULE_20949b5f2d7f8f08fcb7+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a2bb7a84728f6d139c0208a3c816e3293734e61563ff15db4d21b14ee96e56
+size 7834624

neuronxcc-2.19.8089.0+8ab9f450/MODULE_41a325511679b7ebebbb+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_41a325511679b7ebebbb+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe443cb6ddab103141e5407a50d328a4de66f300addabcdd4ca14ea9e036d2a6
+size 2492562

neuronxcc-2.19.8089.0+8ab9f450/MODULE_41a325511679b7ebebbb+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5d0936d544c150b84aa2487c9130647dc04d0f07f00401cba5104acde6b09c
+size 3687424

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a0bd1682d0a0c11db07+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a0bd1682d0a0c11db07+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:929512f2632f1c8a585b155a15770ccec52099aa9eb125d3c47a0b9093ef724f
+size 2079122

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a0bd1682d0a0c11db07+a9d440f5/model.log

@@ -0,0 +1,3 @@
+Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/token_generation_model/_tp0_bk0/model.MODULE_6a0bd1682d0a0c11db07+a9d440f5.hlo_module.pb', '--output', '/tmp/nxd_model/token_generation_model/_tp0_bk0/model.MODULE_6a0bd1682d0a0c11db07+a9d440f5.neff', '--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_model/_tp0_bk0/log-neuron-cc.txt', '--enable-internal-neff-wrapper', '--verbose=35']: [XCG815]  Estimated peak HBM usage (68.697182) exceeds 16GB. Neff won't be able to load on chip - 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.
+2025-07-11T02:24:02Z Non-signal exit. Backend exited with code 1 and stderr: [XCG815]  Estimated peak HBM usage (68.697182) exceeds 16GB. Neff won't be able to load on chip - 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.
+

neuronxcc-2.19.8089.0+8ab9f450/MODULE_981fee31185da34ed5e1+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_981fee31185da34ed5e1+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d40dbe174c4e14d65b28622dd2055e3e97843b72c7c43f6cd0d8f7c72861715
+size 2044560

neuronxcc-2.19.8089.0+8ab9f450/MODULE_981fee31185da34ed5e1+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8253734319b1ba5fcbdc7b0a8638a14149f3c26af8f7d422f4954c0428756273
+size 8274944

neuronxcc-2.19.8089.0+8ab9f450/MODULE_981fee31185da34ed5e1+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55ff7e02a27f3db5520011725e686da2573f47ca69f608fb61b9ac28f60f147
+size 8767488