Test CUDA Builds

Revert "Revert "Arm backend: Enable pytest VKML op unit testing in ciflow/trunk"" #3127

Sign in to view logs

Triggered via pull request November 16, 2025 10:16

zingo

opened #15843

revert-15841-revert-14109-ci

Status Failure

Total duration 1h 18m 20s

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

Annotations

6 errors and 2 warnings

test-model-cuda-e2e (openai, whisper-small, quantized-int4-weight-only) / linux-job

Process completed with exit code 1.

test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job

Process completed with exit code 1.

test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job

Process completed with exit code 1.

test-model-cuda-e2e (openai, whisper-small, non-quantized) / linux-job

Process completed with exit code 1.

test-model-cuda-e2e (openai, whisper-small, quantized-int4-tile-packed) / linux-job

Process completed with exit code 1.

test-model-cuda-e2e (openai, whisper-large-v3-turbo, non-quantized) / linux-job

Process completed with exit code 1.

test-model-cuda-e2e (openai, whisper-small, quantized-int4-tile-packed) / linux-job

Back off 12.405 seconds before retry.

test-model-cuda-e2e (openai, whisper-small, quantized-int4-tile-packed) / linux-job

Failed to download action 'https://api.github.com/repos/aws-actions/configure-aws-credentials/tarball/ececac1a45f3b08a01d2dd070d28d111c5fe6722'. Error: Response status code does not indicate success: 502 (Bad Gateway). 877C:2F5EDA:2D9573:CBFB2F:6919AFA5

Artifacts

Produced during runtime

Name	Size	Digest
google-gemma-3-4b-it-cuda-non-quantized	7.22 GB	`sha256:68dcfa4b9f79f0c2e6bb11f369d516f272434983c225d24e4edbab7f4968a55e`
google-gemma-3-4b-it-cuda-quantized-int4-tile-packed	4.03 GB	`sha256:e28605503e1e71f8d0ac3ee4e43dc6e541a1680db6de8d0f691231a4888b2396`
mistralai-Voxtral-Mini-3B-2507-cuda-non-quantized	6.82 GB	`sha256:1b6f2dc466eaa25ec1abe0a1d980ca6231610ce0458d92c83af5d1f41b4b4ca8`
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-tile-packed	2.89 GB	`sha256:e59e7402d3475dcf5105c758091e3fb875d3da647275b6e224dd6afadb7ce60e`
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-weight-only	6.14 GB	`sha256:93fdf8e64cd777b9f54f33fba7d568ff425888d1cc1644fa397eb6bb797feff9`
openai-whisper-large-v3-turbo-cuda-non-quantized	1.17 GB	`sha256:bc96a2ed24f533c2e0c3643de51d8e58f3f48a7c36f2fc22f5d69403d344e9dc`
openai-whisper-large-v3-turbo-cuda-quantized-int4-tile-packed	490 MB	`sha256:a17369d175c9088a05735703ff46797f67ba7790c9b33a4b378c8b479efa2885`
openai-whisper-large-v3-turbo-cuda-quantized-int4-weight-only	484 MB	`sha256:2623f0dc0e3d7a038525aea4bd69426e98be9903a3513c0a93b248e072acd304`
openai-whisper-small-cuda-non-quantized	361 MB	`sha256:514b0a8fa4e1bbda43ff84ef96f946ec7325f06e42be4fdb6e5d2770dcb63b1c`
openai-whisper-small-cuda-quantized-int4-tile-packed	172 MB	`sha256:94d64c1d2e03ef16e68271b8b89d7edb9f44039b8eb1a1478471bc7f83a9a0c2`
openai-whisper-small-cuda-quantized-int4-weight-only	270 MB	`sha256:0f96e1f7169b5c15927d34263267a2394cd300bcd787599fd8a8419abf6140f6`