trevor-m opened a new pull request #7967: URL: https://github.com/apache/tvm/pull/7967
This PR has some bug fixes and new features for TRT BYOC. * Support scalars in explicit batch mode (when `use_implicit_batch=False`). * Support reduce to scalar for all reduce ops * Mark reduce operators as computationally intensive during subgraph pruning. Default TVM reduce performs poorly on Jetson devices, so we want to offload to TRT in those cases. * Support split operator (with unit tests) -- 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]
