[ET-VK][testing] Add per-shader timing breakdown to benchmark output #8126
Triggered via pull request
February 5, 2026 23:28
pytorchbot
Status
Failure
Total duration
1h 19m 39s
Artifacts
14
cuda.yml
on: pull_request
Matrix: export-model-cuda-artifact
Matrix: test-cuda-builds
unittest-cuda
/
linux-job
24m 38s
Matrix: test-models-cuda
Matrix: test-model-cuda-e2e
check-all-cuda-builds
4s
Annotations
1 error
|
test-model-cuda-e2e (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
Process completed with exit code 1.
|
Artifacts
Produced during runtime
| Name | Size | Digest | |
|---|---|---|---|
|
google-gemma-3-4b-it-cuda-non-quantized
|
7.22 GB |
sha256:a1e4883982e6233719115655072c803a448ac2b94d9171a49b14883b861d9e1b
|
|
|
google-gemma-3-4b-it-cuda-quantized-int4-tile-packed
|
3.36 GB |
sha256:df895e571bfe69ad35e6608bdfe8e0618018119f834cfc841ee359e53da736b8
|
|
|
mistralai-Voxtral-Mini-3B-2507-cuda-non-quantized
|
6.82 GB |
sha256:e87dbcfb7400ced78897c5823d597eb45f514190d4d10aa28922d5f2f27a9040
|
|
|
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-tile-packed
|
2.8 GB |
sha256:41cf09a5678959889a3b89563c891c130f172153a4d7cd3b42b51497106dda8e
|
|
|
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-weight-only
|
6.14 GB |
sha256:7498b4b9e5d8be96f616685274fcbd5a279798fe75b6db8122b1339f7d9cd30e
|
|
|
nvidia-parakeet-tdt-cuda-non-quantized
|
952 MB |
sha256:0e351f636f31650dd4a90ea07cca7cbe504acf3aecfa44b2228d77d5f2a8bbe3
|
|
|
nvidia-parakeet-tdt-cuda-quantized-int4-tile-packed
|
443 MB |
sha256:c75f59bbf80175d04cacd7ced8513dcf413d36f8ad84d973d9da84de0148c71b
|
|
|
nvidia-parakeet-tdt-cuda-quantized-int4-weight-only
|
430 MB |
sha256:341cb6c5801a698ad4dba936dca0ac4fac2ab9260815c978a673268e735f222e
|
|
|
openai-whisper-large-v3-turbo-cuda-non-quantized
|
1.18 GB |
sha256:3daa2d425ac2fe5d8affc51b4c830144d631c23970a7338f7268477c4e024ff9
|
|
|
openai-whisper-large-v3-turbo-cuda-quantized-int4-tile-packed
|
491 MB |
sha256:e5d67ef029968dc84813c8b5b06a15cee4bf50dfc5c03f9bc645115e11e28b0c
|
|
|
openai-whisper-large-v3-turbo-cuda-quantized-int4-weight-only
|
485 MB |
sha256:9f62f9c30c02c69c8e3a8e0e752ad94010548575de9c5861a29d134a7c35fd9c
|
|
|
openai-whisper-small-cuda-non-quantized
|
361 MB |
sha256:3e042aab7cb13b6df6425d922f815c3cb969f8319b51baf8455811282d1d572b
|
|
|
openai-whisper-small-cuda-quantized-int4-tile-packed
|
172 MB |
sha256:93e2945c45f47200e24ad72a0e9df7613076b372bbccc8315151236ecb187983
|
|
|
openai-whisper-small-cuda-quantized-int4-weight-only
|
270 MB |
sha256:0d58d58093048c0a0805181ef9cd77e477ab5a9075ab0ea933a353b305f089f0
|
|