Skip to content
Test CUDA Builds

[Executorch][llm] Fix flakyness of quantized sdpa test #2864

Sign in to view logs

[Executorch][llm] Fix flakyness of quantized sdpa test

[Executorch][llm] Fix flakyness of quantized sdpa test #2864

Run time

Learn about OS pricing on GitHub Actions
Job Run time
test-models-cuda (resnet18) / linux-job
23m 39s
test-models-cuda (conv1d) / linux-job
22m 42s
test-models-cuda (linear) / linux-job
22m 52s
test-models-cuda (add_mul) / linux-job
22m 52s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
21m 8s
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job
20m 55s
test-models-cuda (add) / linux-job
22m 46s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
20m 43s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
20m 47s
export-model-cuda-artifact (openai, whisper-small, quantized-int4-weight-only) / linux-job
20m 53s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
20m 57s
export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
20m 42s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
20m 45s
export-model-cuda-artifact (openai, whisper-small, quantized-int4-tile-packed) / linux-job
21m 5s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, non-quantized) / linux-job
20m 49s
test-executorch-cuda-build-13.0 / linux-job
18m 57s
test-executorch-cuda-build-12.6 / linux-job
20m 43s
export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job
20m 49s
test-executorch-cuda-build-12.8 / linux-job
21m 17s
test-model-cuda-e2e
0s
benchmark-model-cuda
0s
check-all-cuda-builds
2s
6h 45m 23s