AndrewZhaoLuo opened a new issue #8296: URL: https://github.com/apache/tvm/issues/8296
RFC: https://github.com/apache/tvm-rfcs/pull/6 - [ ] Write initial mixed precision pass (https://github.com/apache/tvm/pull/8069) - [ ] Extend support for CUDA backend (https://github.com/apache/tvm/issues/8294) - [ ] Extend support for Vulkan backend (https://github.com/apache/tvm/issues/8295) - [ ] Extend pass to support Algebraic Data Types in Relay - [ ] Ensure bfloat16 works with pass on select GPUs Tasks which may help: - [ ] Get dedup extraneous casts pass completed and refactor existing pass (https://github.com/apache/tvm/pull/8081) Benchmarking improvements from pass: https://docs.google.com/spreadsheets/d/12lgyfuHaRS-X4uG-1iQOV8oAuPpuVAbspcmkOSPRFHQ/edit?usp=sharing -- 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]
