LightLLM
Lightweight, scalable Python LLM inference and serving framework focused on high throughput.
About
LightLLM is a Python-based LLM inference and serving framework from ModelTC. It draws from FasterTransformer, TGI, vLLM, and FlashAttention, and uses a tri-process asynchronous design with token-level KV cache management. The project targets high-throughput serving of large models on modern NVIDIA GPUs.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- LLM Inference & Serving
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Apache-2.0
- Added
- May 7, 2026
Related Tools
Port of Meta's LLaMA model in C/C++ for efficient CPU inference
High-throughput LLM serving engine with PagedAttention
Minimalist ML framework in Rust by Hugging Face for fast inference.
Optimized inference library for running quantized LLMs on consumer GPUs.
Open-source ChatGPT alternative that runs 100% offline on your computer.
Fast LLM inference on consumer GPUs using neuron-aware sparse computation.