2,364 stars | 331 forks | Python
TokenSpeed is a speed-of-light LLM inference engine.
What it does
TokenSpeed is a high-performance LLM inference engine designed specifically for agentic workloads, aiming for speed comparable to TensorRT-LLM and usability like vLLM. Its key innovation is a separation of control and execution planes, enhancing both performance and safety, and it's backed by significant hardware vendor support. This makes it a compelling option for production environments requiring fast and reliable LLM inference.
Why it matters: 🚀 Supercharge your LLM agents! TokenSpeed delivers blazing-fast inference with a unique architecture & serious vendor backing. ⚡️
Trending today with 25 new stars
Want to create content about this repo? Use Nemati AI tools to generate articles, tutorials, and social posts.



