Test CUDA Builds

[ET-VK] Fix softmax NaN and depthwise conv correctness bugs #10505

Sign in to view logs

Triggered via pull request March 5, 2026 00:29

SS-JIA

synchronize #17861

gh/SS-JIA/457/orig

Status Failure

Total duration 42m 9s

Artifacts 18

cuda.yml

on: pull_request

Matrix: export-model-cuda-artifact

Matrix: test-cuda-builds

unittest-cuda / linux-job

Matrix: test-models-cuda

Matrix: test-cuda-pybind

Waiting for pending jobs

Matrix: test-model-cuda-e2e

Waiting for pending jobs

check-all-cuda-builds

Annotations

1 error

export-model-cuda-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job

Process completed with exit code 1.

Artifacts

Produced during runtime

Name	Size	Digest
Qwen-Qwen3-0.6B-cuda-non-quantized Expired	1.1 GB	`sha256:0f52db49dead9ae70f26ba2903c154c01b09e13b3d2b2a457ac96f756f382827`
Qwen-Qwen3-0.6B-cuda-quantized-int4-tile-packed Expired	559 MB	`sha256:796eb74d1dd61603a5fa22696939b7a6336b529490975d59d7a9f606b5e0fd7e`
Qwen-Qwen3-0.6B-cuda-quantized-int4-weight-only Expired	1.1 GB	`sha256:5fcec1f16ac7e21416dcf129c8e3cc6e624862bdc7b638a25cb322070dfcef77`
google-gemma-3-4b-it-cuda-non-quantized Expired	7.22 GB	`sha256:bed65324a990d76389684e8b19d7d2043a2e677d92704b831cf0d28769fb2ecd`
google-gemma-3-4b-it-cuda-quantized-int4-tile-packed Expired	3.36 GB	`sha256:e0fa1e93883a4a4f36d29c87c1af343b46a9cb99386a0ddb1474b7375d63c560`
mistralai-Voxtral-Mini-3B-2507-cuda-non-quantized Expired	6.82 GB	`sha256:d905947260b4f0f1a95bc876d0c04b14b3dbaaeab5bca9430588ae49920e1c90`
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-tile-packed Expired	2.8 GB	`sha256:61bfcfda6450bcffefd724212bf94244fd3f415e56f1107388006594d540fc43`
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-weight-only Expired	6.14 GB	`sha256:ed3c0b11828a2ce628ecf2288233a6986b2af0422624ca254157cd47a6b07b30`
mistralai-Voxtral-Mini-4B-Realtime-2602-cuda-quantized-int4-tile-packed Expired	12.9 GB	`sha256:3e8f6ed86b106f91d804198b0ef011579313781c89bd3b69d6e1378c1191d517`
nvidia-parakeet-tdt-cuda-non-quantized Expired	952 MB	`sha256:c964059d1047514e78f958030b82b27ee89c3befe4e09357f78a22201389efa1`
nvidia-parakeet-tdt-cuda-quantized-int4-tile-packed Expired	443 MB	`sha256:6b9315495d8e531e82b640e7cac3b7744826c446e710c66bc08f90ce8f2ab02b`
nvidia-parakeet-tdt-cuda-quantized-int4-weight-only Expired	430 MB	`sha256:1120f18a8e36d31878161e729edc3b3a8e4e8bd679204055c20a0f58f1508269`
openai-whisper-large-v3-turbo-cuda-non-quantized Expired	1.18 GB	`sha256:1255e1a79793d54070fc46c4b4e78bcdab9553afa927acc0a88ac307ca3f32ca`
openai-whisper-large-v3-turbo-cuda-quantized-int4-tile-packed Expired	491 MB	`sha256:9e9e6d377bb31fcc5c8947b2da9e6ae7f44c3d1b7fcf2455f9ff6457c1bdf1dc`
openai-whisper-large-v3-turbo-cuda-quantized-int4-weight-only Expired	485 MB	`sha256:28c620143f1a1b397ca07eec470534de244bb0764b2b62645beeed1dbb532dfa`
openai-whisper-small-cuda-non-quantized Expired	361 MB	`sha256:0890d8af6c863cf646f91d9a882970fb2fd3f836a39c866320e0172931d9e353`
openai-whisper-small-cuda-quantized-int4-tile-packed Expired	172 MB	`sha256:bdbd6cd7dd15f112fa141b9aed8710d0111becdeb935fc7f5bf74c91cc3a62fc`
openai-whisper-small-cuda-quantized-int4-weight-only Expired	271 MB	`sha256:0ceebefbed1a1c667f18fda7793d37cf3ede85977d3f6b033ca1f74abdd61775`