Skip to content
Test CUDA Builds

[cuda backend] skip fully-masked KV blocks calculation in SDPA #13925

Sign in to view logs

[cuda backend] skip fully-masked KV blocks calculation in SDPA

[cuda backend] skip fully-masked KV blocks calculation in SDPA #13925

Run time

Learn about OS pricing on GitHub Actions
Job Run time
Get changed files / get-changed-files
3s
CI run decision / decide
30s
test-models-cuda / linux-job
46m 19s
unittest-cuda / linux-job
45m 33s
test-executorch-cuda-build-13.0 / linux-job
16m 10s
test-executorch-cuda-build-12.6 / linux-job
18m 55s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
31m 17s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
31m 33s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
24m 18s
export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
33m 28s
export-model-cuda-artifact (Qwen, Qwen3-0.6B, non-quantized) / linux-job
21m 35s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
29m 41s
export-model-cuda-artifact (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
34m 22s
export-model-cuda-artifact (SocialLocalMobile, gemma-4-31B-it-HQQ-INT4, quantized-int4-tile-packed) / linux-job
1d 0h 0m 0s
export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job
21m 15s
export-model-cuda-artifact (Qwen, Qwen3-0.6B, quantized-int4-tile-packed) / linux-job
21m 38s
export-model-cuda-artifact (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
18m 5s
export-model-cuda-artifact (nvidia, parakeet-tdt, non-quantized) / linux-job
27m 4s
export-model-cuda-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
28m 54s
export-model-cuda-artifact (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
29m 40s
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job
33m 56s
export-model-cuda-artifact (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
1d 0h 0m 0s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
22m 29s
check-all-cuda-builds
3s
test-model-cuda-e2e
0s
test-cuda-pybind
-1s
2d 8h 56m 47s