[float8] improve eager numerics for dynamic scales and gets on par with torch.compile #1239
Triggered via pull request
September 26, 2024 20:37
Status
Cancelled
Total duration
7m 39s
Artifacts
–
Annotations
1 error
test (SM-89, linux.g6.4xlarge.experimental.nvidia.gpu, --pre torch --index-url https://download.p... / linux-job
Canceling since a higher priority waiting request for 'float8_test-Run Float8 Tests-refs/pull/904/merge' exists
|