Skip to content
Test CUDA Builds

Remove unnecessary cuda sync for better perf #9383

Sign in to view logs

Remove unnecessary cuda sync for better perf

Remove unnecessary cuda sync for better perf #9383

Run time

Learn about OS pricing on GitHub Actions
Job Run time
unittest-cuda / linux-job
25m 3s
test-executorch-cuda-build-12.8 / linux-job
19m 28s
test-executorch-cuda-build-12.9 / linux-job
21m 40s
test-executorch-cuda-build-13.0 / linux-job
18m 33s
test-executorch-cuda-build-12.6 / linux-job
19m 8s
test-models-cuda (resnet18) / linux-job
22m 35s
test-models-cuda (add_mul) / linux-job
21m 10s
test-models-cuda (mv3) / linux-job
28m 48s
test-models-cuda (sdpa) / linux-job
21m 21s
test-models-cuda (add) / linux-job
21m 22s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
33m 14s
export-model-cuda-artifact (nvidia, parakeet-tdt, non-quantized) / linux-job
27m 56s
export-model-cuda-artifact (openai, whisper-small, quantized-int4-weight-only) / linux-job
23m 29s
test-models-cuda (conv1d) / linux-job
21m 23s
export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job
23m 15s
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job
36m 49s
test-models-cuda (linear) / linux-job
21m 15s
test-models-cuda (mv2) / linux-job
28m 14s
export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
35m 48s
export-model-cuda-artifact (nvidia, parakeet-tdt, quantized-int4-weight-only) / linux-job
28m 19s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
33m 41s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
24m 57s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, non-quantized) / linux-job
24m 10s
export-model-cuda-artifact (openai, whisper-small, quantized-int4-tile-packed) / linux-job
23m 57s
export-model-cuda-artifact (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
29m 51s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
34m 42s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
25m 16s
check-all-cuda-builds
2s
test-cuda-pybind (gemma3-4b, --quantize) / linux-job
24m 12s
test-cuda-pybind (gemma3-4b) / linux-job
25m 23s
test-model-cuda-e2e (nvidia, parakeet-tdt, non-quantized) / linux-job
17m 2s
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
18m 23s
test-model-cuda-e2e (openai, whisper-small, quantized-int4-tile-packed) / linux-job
31m 1s
test-model-cuda-e2e (openai, whisper-small, quantized-int4-weight-only) / linux-job
31m 31s
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
17m 6s
test-model-cuda-e2e (openai, whisper-large-v3-turbo, non-quantized) / linux-job
31m 22s
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
31m 37s
test-model-cuda-e2e (openai, whisper-small, non-quantized) / linux-job
31m 37s
test-model-cuda-e2e (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
16m 58s
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
31m 22s
test-model-cuda-e2e (google, gemma-3-4b-it, non-quantized) / linux-job
18m 49s
test-model-cuda-e2e (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
17m 29s
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
18m 34s
test-model-cuda-e2e (nvidia, parakeet-tdt, quantized-int4-weight-only) / linux-job
16m 52s
17h 54m 44s