Skip to content

Conversation

@yeahdongcn
Copy link
Collaborator

@yeahdongcn yeahdongcn commented Sep 23, 2024

This PR enables VMM support for MUSA to address the request in this discussion. Previously, VMM was disabled in this PR due to a runtime issue.

Testing done

  • make GGML_MUSA=1 -> passed
  • perform about 20 rounds of chatting on MTT S80/S4000 -> passed

@yeahdongcn
Copy link
Collaborator Author

Hi @slaren, the code changes are ready. I'll ask for your review once the runtime issue has been resolved. Thanks in advance.

Signed-off-by: Xiaodong Ye <[email protected]>
@yeahdongcn yeahdongcn marked this pull request as ready for review September 25, 2024 07:51
@yeahdongcn
Copy link
Collaborator Author

Hi @slaren, the code changes are ready. I'll ask for your review once the runtime issue has been resolved. Thanks in advance.

Verified on our daily build, the panic issue is confirmed to be fixed.

@yeahdongcn
Copy link
Collaborator Author

@slaren Please review when you're available. Thanks!

@slaren slaren merged commit 7691654 into ggml-org:master Sep 26, 2024
53 checks passed
dsx1986 pushed a commit to dsx1986/llama.cpp that referenced this pull request Oct 29, 2024
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 15, 2024
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 18, 2024
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