SGLang is a high-performance serving framework for large language models and multimodal models.
GPU serving engine for open-weight models behind an OpenAI-compatible API.
- 言語
- Python
- ライセンス
- Apache-2.0
- スター
- 37k
- 最新リリース
- v0.5.21
- 最終プッシュ
- 2026-10-06
A high-throughput and memory-efficient inference and serving engine for LLMs
代替1件
SGLang is a high-performance serving framework for large language models and multimodal models.
GPU serving engine for open-weight models behind an OpenAI-compatible API.