持续追踪仓库演化，不只看 diff，也看讨论、风险和演进方向。

SGLang is a high-performance serving framework for large language models and multimodal models.

A high-throughput and memory-efficient inference and serving engine for LLMs

High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

verl: Volcano Engine Reinforcement Learning for LLMs

slime is an LLM post-training framework for RL Scaling.