tensorrt-llm
Optimizes LLM inference using NVIDIA TensorRT for high throughput and low latency on NVIDIA GPUs, enhancing production deployment.
Install this skill
or
tensorrt-llm4 files
Comments
Sign in to leave a comment.
No comments yet. Be the first to comment!
GitHub Stars 185.0K
Rate this skill
Categorydevelopment
UpdatedOctober 7, 2026
NousResearch/hermes-agent