jinhongyii opened a new pull request, #16678: URL: https://github.com/apache/tvm/pull/16678
LowBatchGemv rule only apply to function with spatial symbolic var, so that this rule skips matmul in attention kernel which has symbolic_var `kv_seq_len` -- 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]
