Skip to content
Test CUDA Builds

Reduce allocation overhead in quantized sdpa #4137

Sign in to view logs

Reduce allocation overhead in quantized sdpa

Reduce allocation overhead in quantized sdpa #4137

Run time

Learn about OS pricing on GitHub Actions
Job Run time
test-models-cuda (add_mul) / linux-job
22m 9s
test-models-cuda (conv1d) / linux-job
21m 54s
test-models-cuda (sdpa) / linux-job
21m 56s
test-models-cuda (resnet18) / linux-job
22m 28s
test-models-cuda (linear) / linux-job
21m 35s
test-executorch-cuda-build-12.9 / linux-job
21m 25s
test-models-cuda (add) / linux-job
21m 45s
test-executorch-cuda-build-12.8 / linux-job
19m 27s
test-executorch-cuda-build-12.6 / linux-job
19m 34s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
25m 53s
test-executorch-cuda-build-13.0 / linux-job
18m 1s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
34m 7s
export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job
23m 21s
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job
36m 12s
export-model-cuda-artifact (openai, whisper-small, quantized-int4-tile-packed) / linux-job
24m 22s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, non-quantized) / linux-job
24m 42s
export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
36m 43s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
34m 30s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
7m 54s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
33m 51s
export-model-cuda-artifact (openai, whisper-small, quantized-int4-weight-only) / linux-job
23m 43s
check-all-cuda-builds
2s
test-model-cuda-e2e
0s
8h 35m 34s