MasterJH5574 opened a new pull request, #17237: URL: https://github.com/apache/tvm/pull/17237
This PR reorganizes the attention kernel invocation logic in the PagedKVCache, so that in cases of sequence fork, we can effectively merge one ragged-prefill kernel and a decode kernel into a single decode kernel. -- 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