vinx13 opened a new pull request, #14371: URL: https://github.com/apache/tvm/pull/14371
This PR added Relax VM builtin functions to execute with CUDA graph. * `vm.builtin.get_cached_alloc`: Allocate and cache storage objects for future vm invocation * `vm.builtin.get_captured_cuda_graph`: Capture the CUDA graph using CUDA API and save in the cache * `vm.builtin.launch_cuda_graph`: Launch the CUDA graph. The graph rewriting to enable CUDA graph backend will be done in a separate PR. -- 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]
