Upgrade Docker container from gcc9 to gcc11 and add gcc9-nopytorch variant #4578
mergennachincuda.yml
on: pull_request
Matrix: export-model-cuda-artifact
Matrix: test-cuda-builds
Matrix: test-models-cuda
Matrix: test-model-cuda-e2e
check-all-cuda-builds
4s
Artifacts
Produced during runtime
| Name | Size | Digest | |
|---|---|---|---|
|
google-gemma-3-4b-it-cuda-non-quantized
|
7.22 GB |
sha256:bb14c9a9032a0012daa2daaadd219c214cb9a10536d6fc2936b0a416729c01da
|
|
|
google-gemma-3-4b-it-cuda-quantized-int4-tile-packed
|
3.36 GB |
sha256:c76aa41b139965ab26ced04721a20edcdfbbabf70b48ef35df2f34a832bf8676
|
|
|
mistralai-Voxtral-Mini-3B-2507-cuda-non-quantized
|
6.82 GB |
sha256:580f6ddcd67796a4a4f077dd0750ef7af8818265d09f09aa307ba61616faca88
|
|
|
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-tile-packed
|
2.89 GB |
sha256:954e007224f9d59bc969658e4f3ca9782c930743adcf463637e68c0e671f82b1
|
|
|
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-weight-only
|
6.14 GB |
sha256:2f1bf38876608b5383e8bcab3be27f3af59db2e1b2c817469319c7904bfaa4e8
|
|
|
openai-whisper-large-v3-turbo-cuda-non-quantized
|
1.18 GB |
sha256:134114d7909e7c860ab9aa72772d38d32df2cec264954b5107998b4998e128fd
|
|
|
openai-whisper-large-v3-turbo-cuda-quantized-int4-tile-packed
|
491 MB |
sha256:c66f5eed5a99dcb3de47823284677a0bcfd377bff11b72a35801e049c038a7a8
|
|
|
openai-whisper-large-v3-turbo-cuda-quantized-int4-weight-only
|
485 MB |
sha256:cfa1c89dc1edf68437e3447b03a93235e01d16391455a8888be55423b64eb78e
|
|
|
openai-whisper-small-cuda-non-quantized
|
361 MB |
sha256:d59a47be24e8513671a43e0e49b27311f9dcd940f334a96ede660fa1d548e390
|
|
|
openai-whisper-small-cuda-quantized-int4-tile-packed
|
172 MB |
sha256:5a4d8bb18058f969a111875a91806b62778c433eff0a6b100bc7d5b5753b2c3f
|
|
|
openai-whisper-small-cuda-quantized-int4-weight-only
|
270 MB |
sha256:c4e5d699204e195bebe1410450014e9564b57e9f4ae50a797da4faa430f1777d
|
|