MasterJH5574 opened a new pull request, #16374: URL: https://github.com/apache/tvm/pull/16374
This PR supports PagedKVCache with leveraging TIR kernels. Right now we do not have sufficient TIR kernels for multi-level sequences in PagedKVCache, therefore `Fork` in PagedKVCache is disabled when such a function does not exist. This PR adds a "reduced" creator of PagedKVCache, where some auxiliary functions such as the begin/end forward function of prefill/decode default to None. CUDA tests are added to ensure correctness. Co-authored-by: Hongyi Jin <[email protected]> Co-authored-by: Bohan Hou <[email protected]> -- 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]
