NVIDIA/TensorRT-LLM

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

Latest release v1.2.1 · 20 Apr 2026

46 files for Claude Code, Codex and OpenCode: exec-compile-specialist, exec-local-slurm, exec-remote-slurm, kernel-cuda-specialist and 42 more — 3,656 tokens loaded in every session.