tensorrtllm_backend icon indicating copy to clipboard operation
tensorrtllm_backend copied to clipboard

Published 20 hours ago • verified publisher icon triton-inference-server

Support python runtime

Open avianion opened this issue 8 months ago • 0 comments

Triton inference server supports C++ runtime for Tensorrtllm.

But would be great to support also Python runtime

avianion avatar Jul 01 '24 02:07 avianion