Skip to content
Test CUDA Builds

Fix FuseMMWithAdd returning False after graph mutation #13099

Sign in to view logs

Fix FuseMMWithAdd returning False after graph mutation

Fix FuseMMWithAdd returning False after graph mutation #13099

Run time

Learn about OS pricing on GitHub Actions
Job Run time
test-executorch-cuda-build-12.9 / linux-job
21m 54s
test-executorch-cuda-build-12.8 / linux-job
18m 11s
test-executorch-cuda-build-12.6 / linux-job
16m 5s
test-models-cuda / linux-job
43m 32s
test-executorch-cuda-build-13.0 / linux-job
16m 9s
unittest-cuda / linux-job
44m 34s
export-model-cuda-artifact (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
17m 43s
export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
32m 57s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
30m 44s
export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job
20m 43s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
31m 2s
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job
33m 30s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
22m 37s
export-model-cuda-artifact (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
27m 32s
export-model-cuda-artifact (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
32m 23s
export-model-cuda-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
28m 41s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
31m 24s
export-model-cuda-artifact (Qwen, Qwen3-0.6B, non-quantized) / linux-job
21m 27s
export-model-cuda-artifact (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
1h 13m 48s
export-model-cuda-artifact (nvidia, parakeet-tdt, non-quantized) / linux-job
25m 45s
export-model-cuda-artifact (Qwen, Qwen3-0.6B, quantized-int4-tile-packed) / linux-job
21m 48s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
22m 3s
check-all-cuda-builds
4s
test-cuda-pybind (gemma3-4b, --quantize, google-gemma-3-4b-it-cuda-quantized-int4-tile-packed) / linux-job
22m 13s
test-cuda-pybind (qwen3-0.6b, --quantize, Qwen-Qwen3-0.6B-cuda-quantized-int4-tile-packed) / linux-job
2h 1m 5s
test-cuda-pybind (qwen3-0.6b, Qwen-Qwen3-0.6B-cuda-non-quantized) / linux-job
2h 1m 31s
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
15m 6s
test-model-cuda-e2e (openai, whisper-small, non-quantized) / linux-job
30m 10s
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
30m 10s
test-model-cuda-e2e (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
30m 56s
test-model-cuda-e2e (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
14m 58s
test-model-cuda-e2e (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
15m 20s
test-model-cuda-e2e (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
14m 57s
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
29m 0s
test-model-cuda-e2e (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
14m 57s
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
16m 48s
test-model-cuda-e2e (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
43m 54s
test-model-cuda-e2e (nvidia, parakeet-tdt, non-quantized) / linux-job
15m 5s
test-model-cuda-e2e (google, gemma-3-4b-it, non-quantized) / linux-job
16m 40s
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
15m 36s
20h 3m 2s