yzh119 opened a new pull request, #16323: URL: https://github.com/apache/tvm/pull/16323
Mixtral requires `group_size = 4` in Grouped Query Attention which FlashInfer didn't enable (to reduce compilation time) by default. This PR incorporates the hotfix (https://github.com/flashinfer-ai/flashinfer/pull/35) from flashinfer 3rdparty submodule to support Mixtral. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
