AndrewZhaoLuo opened a new issue #8294: URL: https://github.com/apache/tvm/issues/8294
Solve issues and make modifications to support CUDA for mixed precision pass here: https://github.com/apache/tvm/pull/8069 Current initial issues as described by @Lunderberg > On the cuda side, it's failing a check that requires 16-bit floats to be used in pairs. >> Check failed: lanes % 2 == 0 (1 vs. 0) : only support even lane for half type This issue is completed when unit tests can pass for CUDA target. -- 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. For queries about this service, please contact Infrastructure at: [email protected]
