tlopex commented on issue #19609: URL: https://github.com/apache/tvm/issues/19609#issuecomment-4616904760
Hi @guest2180 Thanks for reporting. For now the practical workaround is to disable TensorRT codegen/runtime when using TRT10/CUDA 12.8, or build TVM with an older TensorRT stack such as TRT 8.6.x with a CUDA version supported by that TRT release. If you are interested in working on TensorRT 10 support, contributions would be very welcome. A good first step would be to add a clear version guard for TRT >= 10 so users get an explicit unsupported-version message, then follow up with the actual migration work. -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
