vinx13 commented on PR #17006:
URL: https://github.com/apache/tvm/pull/17006#issuecomment-2140985551
do we need to update cublas codegen or runtime to support the cast?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use
valmat07 opened a new pull request, #17006:
URL: https://github.com/apache/tvm/pull/17006
This PR adds fusing of the astype operation to matmul for cublas. This
change is needed to improve the performance for fp8.
--
This is an automated message from the Apache Git Service.
To respond to