Summary
Jobs
test-executorch-cuda-build-12.6
test-executorch-cuda-build-12.8
test-executorch-cuda-build-13.0
test-models-cuda (linear)
test-models-cuda (add)
test-models-cuda (add_mul)
test-models-cuda (resnet18)
test-models-cuda (conv1d)
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized)
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed)
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only)
export-model-cuda-artifact (openai, whisper-small, non-quantized)
export-model-cuda-artifact (openai, whisper-small, quantized-int4-tile-packed)
export-model-cuda-artifact (openai, whisper-small, quantized-int4-weight-only)
export-model-cuda-artifact (openai, whisper-large-v3-turbo, non-quantized)
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed)
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only)
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized)
export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed)
check-all-cuda-builds
benchmark-model-cuda (mistralai, Voxtral-Mini-3B-2507, non-quantized)
benchmark-model-cuda (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed)
benchmark-model-cuda (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only)
benchmark-model-cuda (google, gemma-3-4b-it, non-quantized)
benchmark-model-cuda (google, gemma-3-4b-it, quantized-int4-tile-packed)
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized)
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed)
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only)
test-model-cuda-e2e (openai, whisper-small, non-quantized)
test-model-cuda-e2e (openai, whisper-small, quantized-int4-tile-packed)
test-model-cuda-e2e (openai, whisper-small, quantized-int4-weight-only)
test-model-cuda-e2e (openai, whisper-large-v3-turbo, non-quantized)
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-tile-packed)
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-weight-only)
test-model-cuda-e2e (google, gemma-3-4b-it, non-quantized)
test-model-cuda-e2e (google, gemma-3-4b-it, quantized-int4-tile-packed)
You can’t perform that action at this time.