Skip to content
Test CUDA Builds

[cuda backend] optimized L_kv threshold for sdpa implementation selection. #13858

Sign in to view logs

[cuda backend] optimized L_kv threshold for sdpa implementation selection.

[cuda backend] optimized L_kv threshold for sdpa implementation selection. #13858

Run time

Learn about OS pricing on GitHub Actions
Job Run time
Get changed files / get-changed-files
5s
CI run decision / decide
32s
test-models-cuda / linux-job
46m 25s
unittest-cuda / linux-job
45m 47s
test-executorch-cuda-build-12.6 / linux-job
18m 17s
test-executorch-cuda-build-13.0 / linux-job
17m 44s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
31m 16s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
31m 29s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
22m 7s
export-model-cuda-artifact (nvidia, parakeet-tdt, non-quantized) / linux-job
26m 59s
export-model-cuda-artifact (Qwen, Qwen3-0.6B, non-quantized) / linux-job
21m 25s
export-model-cuda-artifact (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
17m 33s
export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job
20m 58s
export-model-cuda-artifact (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
34m 5s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
30m 40s
export-model-cuda-artifact (SocialLocalMobile, gemma-4-31B-it-HQQ-INT4, quantized-int4-tile-packed) / linux-job
0s
export-model-cuda-artifact (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
28m 33s
export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
33m 25s
export-model-cuda-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
28m 1s
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job
34m 48s
export-model-cuda-artifact (Qwen, Qwen3-0.6B, quantized-int4-tile-packed) / linux-job
21m 33s
export-model-cuda-artifact (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
0s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
23m 49s
check-all-cuda-builds
3s
8h 55m 34s