Skip to content

[float8nocompile] Add alternate Triton kernels for FP8 conversion which use atomic_max-based algo instead of reduction-based algo #1069

[float8nocompile] Add alternate Triton kernels for FP8 conversion which use atomic_max-based algo instead of reduction-based algo

[float8nocompile] Add alternate Triton kernels for FP8 conversion which use atomic_max-based algo instead of reduction-based algo #1069

Triggered via pull request December 20, 2024 21:52
Status Failure
Total duration 9s
Artifacts

pr-label-check.yml

on: pull_request
Check PR Labels
1s
Check PR Labels
Fit to window
Zoom out
Zoom in

Annotations

2 errors and 1 warning
Check PR Labels
This PR requires at least one label starting with 'topic:'. Available topics can be found at: https://github.com/pytorch/ao/labels?q=topic
Check PR Labels
Process completed with exit code 1.
Check PR Labels
ubuntu-latest pipelines will use ubuntu-24.04 soon. For more details, see https://github.com/actions/runner-images/issues/10636