KnowingNothing opened a new pull request, #16871: URL: https://github.com/apache/tvm/pull/16871
In some scenarios such as speculative decoding, it is possible to pop all the tokens in the last block. This PR allows `PopN` to pop all the tokens in the last block of KV cache. -- 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: commits-unsubscr...@tvm.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
