You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "masahi (via GitHub)" <gi...@apache.org> on 2023/05/25 19:15:56 UTC

[GitHub] [tvm] masahi opened a new pull request, #14957: [Unity][BYOC] Make CUTLASS attention rewriting aware of fp16 <-> f32 casting

masahi opened a new pull request, #14957:
URL: https://github.com/apache/tvm/pull/14957

   In practice, `partition_for_cutlass` is invoked after we run the fp16 conversion pass. The pass adds fp16 -> fp32 and fp32 -> fp16 before / after softmax, but these casts are not recognized by the attention rewriter introduced in https://github.com/apache/tvm/pull/14744. This is fixed in this PR.
   
   I also found and fixed several bugs in the rewriting logic.
   
   @cyx-6 @vinx13  


-- 
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-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] tvm-bot commented on pull request #14957: [Unity][BYOC] Make CUTLASS attention rewriting aware of fp16 <-> f32 casting

Posted by "tvm-bot (via GitHub)" <gi...@apache.org>.
tvm-bot commented on PR #14957:
URL: https://github.com/apache/tvm/pull/14957#issuecomment-1563391083

   <!---bot-comment-->
   
   Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from [Reviewers](https://github.com/apache/incubator-tvm/blob/master/CONTRIBUTORS.md#reviewers) by @-ing them in a comment.
   
   <!--bot-comment-ccs-start-->
    * cc @billishyahao, @quic-sanirudh <sub>See [#10317](https://github.com/apache/tvm/issues/10317) for details</sub><!--bot-comment-ccs-end-->
   
   <sub>Generated by [tvm-bot](https://github.com/apache/tvm/blob/main/ci/README.md#github-actions)</sub>


-- 
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-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] masahi merged pull request #14957: [Unity][BYOC] Make CUTLASS attention rewriting aware of fp16 <-> f32 casting

Posted by "masahi (via GitHub)" <gi...@apache.org>.
masahi merged PR #14957:
URL: https://github.com/apache/tvm/pull/14957


-- 
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-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org