Skip to content
Test CUDA Builds

[ET-VK] Fix softmax NaN and depthwise conv correctness bugs #10452

Sign in to view logs

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

[ET-VK] Fix softmax NaN and depthwise conv correctness bugs #10452

Triggered via pull request March 4, 2026 16:29
@SS-JIASS-JIA
opened #17848
gh/SS-JIA/457/head
Status Success
Total duration 1h 9m 36s
Artifacts 17

cuda.yml

on: pull_request
Matrix: export-model-cuda-artifact
Matrix: test-cuda-builds
unittest-cuda  /  linux-job
25m 16s
unittest-cuda / linux-job
Matrix: test-models-cuda
Matrix: test-cuda-pybind
Matrix: test-model-cuda-e2e
check-all-cuda-builds
2s
check-all-cuda-builds
Fit to window
Zoom out
Zoom in

Artifacts

Produced during runtime
Name Size Digest
Qwen-Qwen3-0.6B-cuda-non-quantized Expired
1.1 GB
sha256:21b233b342e41afd8fc3e93678c39deb247869af4d84459db12b50844775cc12
Qwen-Qwen3-0.6B-cuda-quantized-int4-tile-packed Expired
559 MB
sha256:2c92031c4a4a97fdce571812a4475b36cc60162ec832b775e7acac803e61ec92
Qwen-Qwen3-0.6B-cuda-quantized-int4-weight-only Expired
1.1 GB
sha256:346d946a24c7d4610b9a3f1acf7cd5a9a21507f9b860b1632c257be5c03b0267
google-gemma-3-4b-it-cuda-non-quantized Expired
7.22 GB
sha256:ce462841ec3a992255800dd609c9be5e1652fe12eb1ee4d73ed55a805e73da31
google-gemma-3-4b-it-cuda-quantized-int4-tile-packed Expired
3.36 GB
sha256:fd175d768306410dba8024aa689a7f88446e3ec9bb8343918ed5072993908f29
mistralai-Voxtral-Mini-3B-2507-cuda-non-quantized Expired
6.82 GB
sha256:da69eafa98750990d075820636b246c2f2a0eb4fb2bd59abde0b9ed8dfa242fd
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-tile-packed Expired
2.8 GB
sha256:8bf6022e4b788fc62f42a240a9dfb460ebc1b38992625a8934ab84c798db4754
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-weight-only Expired
6.14 GB
sha256:3cc55812396bb52e63f0d1d120d75f7c55386e33f82f423c2fa6663d93630423
nvidia-parakeet-tdt-cuda-non-quantized Expired
952 MB
sha256:8024f1ce5f9de3b6aea68a423b1d55b577f57c0650c9f8f38e38ae16acd056ba
nvidia-parakeet-tdt-cuda-quantized-int4-tile-packed Expired
443 MB
sha256:ca5f456a900cc7d04ba5013f106964dee4a98647b5521ee23647e3d83f116a8d
nvidia-parakeet-tdt-cuda-quantized-int4-weight-only Expired
430 MB
sha256:456732ed5484a17595075e5647baeecccd99c615eba2f184c63edc82383a46b1
openai-whisper-large-v3-turbo-cuda-non-quantized Expired
1.18 GB
sha256:13d224526f55f39666212dc1f4209b40e65e609e771c167e48f99bc3a3797a0a
openai-whisper-large-v3-turbo-cuda-quantized-int4-tile-packed Expired
491 MB
sha256:a80fa69c541719e977fbab1cc7be553b2e685de6b77d2dfbbb9515ba92b9bfd9
openai-whisper-large-v3-turbo-cuda-quantized-int4-weight-only Expired
485 MB
sha256:a3a82a6847b69feb30699dbc6a779710764ecd42190e55108e252f857f7b952f
openai-whisper-small-cuda-non-quantized Expired
362 MB
sha256:c1120f3da69f65c6ac8e2da5cceb3375c095e3f78c3eaa6db1ed49435b091bf1
openai-whisper-small-cuda-quantized-int4-tile-packed Expired
172 MB
sha256:c764f36b867c6528d7feea4f83a30175b4a37e9f7cc93d3b1f5d53981100ab0b
openai-whisper-small-cuda-quantized-int4-weight-only Expired
271 MB
sha256:c2f074477379710efb878363286d4d1a1cbebf3908d4e9c005dd02e94190f09b