Skip to content
Test CUDA Windows Export and E2E

[cuda backend] optimized L_kv threshold for sdpa implementation selection. #6933

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. #6933

Run time

Learn about OS pricing on GitHub Actions
Job Run time
Get changed files / get-changed-files
4s
CI run decision / decide
32s
export-model-cuda-windows-artifact (nvidia, parakeet-tdt, non-quantized) / linux-job
25m 40s
export-model-cuda-windows-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile... / linux-job
29m 59s
export-model-cuda-windows-artifact (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
16m 4s
export-model-cuda-windows-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
29m 45s
export-model-cuda-windows-artifact (nvidia, parakeet-tdt, quantized-int4-weight-only) / linux-job
26m 6s
export-model-cuda-windows-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
29m 21s
test-model-cuda-windows-e2e (nvidia, parakeet-tdt, quantized-int4-weight-only) / windows-job
34m 5s
test-model-cuda-windows-e2e (nvidia, parakeet-tdt, non-quantized) / windows-job
36m 1s
test-model-cuda-windows-e2e (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / windows-job
34m 38s
test-model-cuda-windows-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / windows-job
35m 21s
test-model-cuda-windows-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / windows-job
35m 58s
test-model-cuda-windows-e2e (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / windows-job
33m 39s
6h 7m 13s