Cydia2018 opened a new pull request, #15753: URL: https://github.com/apache/tvm/pull/15753
Purpose: This PR introduces RocBLAS and RocBLAS tuning support in Unity. Motivation: The industry is asking for diversity of computing power. We at Kwai AIPCG noticed that, as an alternative to Nvidia GPUs, AMD backend is not as optimized as NV Backend in TVM. Thanks to BYOC and AMD RocBLAS Project, we are able to exploit AMD backend performance with relatively low engineering effort. Authors: Kwai AI Platform Compiler Group We are actively working on optimizing Foundational Model inference with AI Compiler techniques and will continuously contribute to TVM community. Please stay tuned. -- 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]
