Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Use tgemm for mi300 only #48

Closed
wants to merge 6 commits into from

Conversation

ppalaniappan-amd
Copy link

@ppalaniappan-amd ppalaniappan-amd commented Jun 13, 2024

[Hardware][H100] rocm/vllm fails on Nvidia H100 with the following error message:
ModuleNotFoundError: No module named 'hipbsolidxgemm'
This PR fixes this issue by using tgemm for MI300 and F.linear for H100.

@sabreshao
Copy link

Does tgemm work on other ROCm devices such as MI200 after this PR is merged?

@ppalaniappan-amd ppalaniappan-amd deleted the ppalania/import_tgemm_for_mi300_only branch September 25, 2024 17:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants