zhuochenKIDD opened a new pull request #7616: URL: https://github.com/apache/tvm/pull/7616
We are currently using graph runtime to run some CTR models on NV-GPU, for our in-house model (around 100 nodes in tvm json graph ) cuGraphLaunch can reduce 5% to 10% percent latency vs the original for-loop cuda kernel launch. So I wonder if the extension might benefits other workloads, I haven't test other types of models. This is a POC, will supplement demos/docs ---------------------------------------------------------------- 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]
