Skip to content
Test CUDA Builds

[Executorch] Use temp allocator for allocating scratch memory #2699

Sign in to view logs

[Executorch] Use temp allocator for allocating scratch memory

[Executorch] Use temp allocator for allocating scratch memory #2699

Triggered via pull request November 10, 2025 17:18
@kimishpatelkimishpatel
opened #15708
gh/kimishpatel/208/head
Status Success
Total duration 1h 11m 4s
Artifacts 11

cuda.yml

on: pull_request
Matrix: export-model-cuda-artifact
Matrix: test-cuda-builds
Matrix: test-models-cuda
Matrix: benchmark-model-cuda
Matrix: test-model-cuda-e2e
check-all-cuda-builds
2s
check-all-cuda-builds
Fit to window
Zoom out
Zoom in

Annotations

29 errors
test-executorch-cuda-build-13.0 / linux-job
clone of 'https://github.com/pytorch-labs/FACTO.git' into submodule path '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/backends/cadence/utils/FACTO' failed
test-executorch-cuda-build-13.0 / linux-job
unable to access 'https://github.com/pytorch-labs/FACTO.git/': The requested URL returned error: 500
test-executorch-cuda-build-13.0 / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
test-executorch-cuda-build-12.6 / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
test-executorch-cuda-build-12.8 / linux-job
clone of 'https://github.com/dvidelabs/flatcc.git' into submodule path '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch/third-party/flatcc' failed
test-executorch-cuda-build-12.8 / linux-job
expected 'packfile'
test-executorch-cuda-build-12.8 / linux-job
RPC failed; HTTP 500 curl 22 The requested URL returned error: 500
test-executorch-cuda-build-12.8 / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
test-models-cuda (linear) / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
test-models-cuda (add) / linux-job
expected 'acknowledgments'
test-models-cuda (add) / linux-job
RPC failed; HTTP 500 curl 22 The requested URL returned error: 500
test-models-cuda (add) / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
test-models-cuda (add_mul) / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
test-models-cuda (conv1d) / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
test-models-cuda (conv1d) / linux-job
expected 'packfile'
test-models-cuda (conv1d) / linux-job
RPC failed; HTTP 500 curl 22 The requested URL returned error: 500
test-models-cuda (resnet18) / linux-job
expected 'packfile'
test-models-cuda (resnet18) / linux-job
RPC failed; HTTP 500 curl 22 The requested URL returned error: 500
export-model-cuda-artifact (openai, whisper-small, quantized-int4-weight-only) / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
export-model-cuda-artifact (openai, whisper-small, quantized-int4-weight-only) / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
export-model-cuda-artifact (openai, whisper-small, quantized-int4-tile-packed) / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
export-model-cuda-artifact (openai, whisper-large-v3-turbo, non-quantized) / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
unable to access 'https://github.com/NVIDIA/cutlass/': The requested URL returned error: 500
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500
export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
unable to access 'https://github.com/pytorch/executorch/': The requested URL returned error: 500

Artifacts

Produced during runtime
Name Size Digest
google-gemma-3-4b-it-cuda-non-quantized Expired
7.22 GB
sha256:f189a0abe2eec69fa612e18abbdbedaf2a0652bc3bebb39c8dbff622f2d5daf4
google-gemma-3-4b-it-cuda-quantized-int4-tile-packed Expired
4.03 GB
sha256:48f60002ffc267ffdda99c0098ab35d423a4211909d7ec73ba133ceb8f572796
mistralai-Voxtral-Mini-3B-2507-cuda-non-quantized Expired
6.82 GB
sha256:26bad68901beb74a8a804aa27e694dbe2ccf61d166974031d1cae2612023125c
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-tile-packed Expired
2.89 GB
sha256:457c1e2cada993c4ed3c5c7182a94ab2e8dec41d3b1b07a142e431538d83aa24
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-weight-only Expired
6.14 GB
sha256:3833d078fb5e455ac01ab95003829f854f6f96ff29711b36390239d1a26f0c8f
openai-whisper-large-v3-turbo-cuda-non-quantized Expired
1.17 GB
sha256:6d289be04688738f30aa74d6d945eec2b9188cdaaa3a9b194180f96c0e807a68
openai-whisper-large-v3-turbo-cuda-quantized-int4-tile-packed Expired
490 MB
sha256:b3f885e4078c10ee79941b6061e376291bc8e909641078ede6317e80363eb962
openai-whisper-large-v3-turbo-cuda-quantized-int4-weight-only Expired
484 MB
sha256:3fd9ba2f837a8a2c2114e6ee7b71b7c0968f4921cbe8661af45a245a37252cdb
openai-whisper-small-cuda-non-quantized Expired
361 MB
sha256:3f01dcdf55ee763b9263eb752a1201d4f9b8af610a230a117394b82721d5df90
openai-whisper-small-cuda-quantized-int4-tile-packed Expired
172 MB
sha256:237107f53bbb6a03cda2978bc146febaaa1f2f7556eef00068a07b4755c23fc6
openai-whisper-small-cuda-quantized-int4-weight-only Expired
270 MB
sha256:07a5742e69d096deb67b17fbe594982d3eb7b17182de9ad956d431dd84033f6b