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
- Stars
- 15k
- Forks
- 2.8k
- Open issues
- 677
- Last push
- today
About TensorRT-LLM
TensorRT-LLM is a free, open-source AI inference tool by NVIDIA, written mainly in Python. 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. It has 15k GitHub stars and 2.8k forks, and was last updated today. GitHub doesn't detect a standard license, so check the repository before using it commercially.
- License
- Not detected
- Language
- Python
- Stars
- 14,917
- Last update
- today
- Runs on Mac
- Not stated
- GPU
- Not stated
- Paid API key
- Not stated
- Self-hostable
- Not stated
Similar free tools
vllm95k stars · A high-throughput and memory-efficient inference and serving engine for LLMs
sglang38k stars · SGLang is a high-performance serving framework for large language models and multimodal models.
BentoML8.9k stars · The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
PowerInfer9.8k stars · High-speed Large Language Model Serving for Local Deployment
TensorRT-LLM FAQ
Is TensorRT-LLM free?
Yes. TensorRT-LLM is open source and free to use. GitHub doesn't detect a standard license, so check the repository before using it commercially.
Does TensorRT-LLM run on a Mac?
Its README doesn't say. Check the installation guide on GitHub before you start.
Does TensorRT-LLM need a GPU?
Its README doesn't state hardware needs. AI models generally run much faster with a GPU.
Is TensorRT-LLM still maintained?
Yes. It was last updated today and has 677 open issues on GitHub.
What are alternatives to TensorRT-LLM?
Similar free, open-source tools include vllm, sglang, BentoML, PowerInfer.