SGLang is a high-performance serving framework for large language models and multimodal models.
Repository Intelligence
持续追踪仓库演化，不只看 diff，也看讨论、风险和演进方向。
仓库列表
A high-throughput and memory-efficient inference and serving engine for LLMs
verl: Volcano Engine Reinforcement Learning for LLMs
High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle
THUDM/slime
监控中slime is an LLM post-training framework for RL Scaling.