{"slug":"tensorrt-llm","name":"TensorRT-LLM","category":"local-inference","categoryName":"Local inference & serving","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"Apache-2.0","maintained":"yes","officialUrl":"https://nvidia.github.io/TensorRT-LLM","repo":"https://github.com/NVIDIA/TensorRT-LLM","latestVersion":"v1.4.0rc1","latestRelease":"2026-10-22","stars":14908,"starsAsOf":"2026-10-22","description":"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.","descriptionZh":"NVIDIA GPU 上的 LLM 推理优化","callMethods":["SDK","API"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["blackwell","cuda","llm-serving","moe","pytorch"],"language":"Python","lastPush":"2026-10-22","formerly":null,"packages":[{"registry":"pypi","name":"tensorrt-llm","url":"https://pypi.org/project/tensorrt-llm/","versionsUrl":"https://pypi.org/project/tensorrt-llm/#history","latestVersion":"1.2.1","latestDate":"2026-04-20"}],"recentVersions":[{"version":"v1.3.0rc23.post1","date":"2026-08-18","prerelease":false,"url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc23.post1","source":"GitHub Release"},{"version":"v1.3.0rc22.post1","date":"2026-08-18","prerelease":false,"url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc22.post1","source":"GitHub Release"}],"alternatives":["vllm","flashinfer","sglang","gpustack","lmcache","stable-diffusion-webui","diffusers","ramalama"],"stacks":[],"scenarios":["switch-models","run-models-locally","use-ai-compliantly-in-china","learn-ai"],"problems":[],"reasonZh":"NVIDIA 推理","sources":["profile","priority","oss","github-oss","github-pool"],"record":"https://aimap.page/api/v1/software/tensorrt-llm.json","pages":{"en":"https://aimap.page/en/software/tensorrt-llm/","zh-hans":"https://aimap.page/zh-hans/software/tensorrt-llm/"}}