[Bug Report] Flash decode with GQA on Llama 3.1 8B shape does not work with (8,7) grid size #5798
Triggered via issue
December 8, 2024 23:31
caixunshiren
Status
Success
Total duration
16s
Artifacts
–
on-community-issue.yaml
on: issues
gh-slack-bridge
3s
Annotations
1 warning
|
gh-slack-bridge
ubuntu-latest pipelines will use ubuntu-24.04 soon. For more details, see https://github.com/actions/runner-images/issues/10636
|