Skip to content
Test CUDA Builds

Add GPU-side Gumbel-max sampling for CUDA graph compatibility #12862

Sign in to view logs

Add GPU-side Gumbel-max sampling for CUDA graph compatibility

Add GPU-side Gumbel-max sampling for CUDA graph compatibility #12862

Run time

Learn about OS pricing on GitHub Actions
Job Run time
unittest-cuda / linux-job
41m 1s
test-models-cuda / linux-job
43m 41s
test-executorch-cuda-build-12.9 / linux-job
21m 12s
test-executorch-cuda-build-13.0 / linux-job
15m 52s
test-executorch-cuda-build-12.6 / linux-job
16m 41s
test-executorch-cuda-build-12.8 / linux-job
17m 39s
export-model-cuda-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
1h 5m 39s
export-model-cuda-artifact (Qwen, Qwen3-0.6B, quantized-int4-tile-packed) / linux-job
22m 2s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
30m 53s
export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
32m 54s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
31m 0s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
31m 52s
export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job
21m 10s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
22m 36s
export-model-cuda-artifact (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
17m 57s
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job
34m 9s
export-model-cuda-artifact (nvidia, parakeet-tdt, non-quantized) / linux-job
1h 31m 5s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
22m 55s
export-model-cuda-artifact (Qwen, Qwen3-0.6B, non-quantized) / linux-job
21m 54s
export-model-cuda-artifact (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
32m 49s
export-model-cuda-artifact (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
42m 15s
export-model-cuda-artifact (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
1h 30m 20s
check-all-cuda-builds
3s
test-cuda-pybind
0s
test-model-cuda-e2e
0s
12h 47m 39s