Skip to content
Test CUDA Windows Export and E2E

[cuda backend] optimized L_kv threshold for sdpa implementation selection. #6893

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. #6893

Run time

Learn about OS pricing on GitHub Actions
Job Run time
CI run decision / decide
32s
Get changed files / get-changed-files
2s
export-model-cuda-windows-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
29m 34s
export-model-cuda-windows-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
29m 33s
export-model-cuda-windows-artifact (nvidia, parakeet-tdt, non-quantized) / linux-job
25m 52s
export-model-cuda-windows-artifact (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
16m 16s
export-model-cuda-windows-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile... / linux-job
30m 13s
export-model-cuda-windows-artifact (nvidia, parakeet-tdt, quantized-int4-weight-only) / linux-job
26m 2s
test-model-cuda-windows-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / windows-job
36m 3s
test-model-cuda-windows-e2e (nvidia, parakeet-tdt, non-quantized) / windows-job
35m 20s
test-model-cuda-windows-e2e (nvidia, parakeet-tdt, quantized-int4-weight-only) / windows-job
36m 15s
test-model-cuda-windows-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / windows-job
35m 42s
test-model-cuda-windows-e2e (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / windows-job
35m 26s
test-model-cuda-windows-e2e (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / windows-job
36m 36s
6h 13m 26s