sglang
https://github.com/sgl-project/sglang
Python
SGLang is a high-performance serving framework for large language models and multimodal models.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to sglang
Help out
- Issues
- Feat/router session stats
- [HiSparse]: size DSV4 C4 device pool by request capacity
- Fix misleading assertion message for speculative decoding
- Codex/minwm async vae multiuser
- Keep chunked prefix bookkeeping when the radix insert is skipped
- Fix/hicache sidecar ok pure mla
- [AMD] Serve Kimi-K3 on gfx942: moonmath MLA multi-query verify, MXFP4 MoE, chunked prefix KV
- [ROCm] Fix gfx942 LDS overflow in DSA bf16 decode under dp-attention
- fix(qwen3-vl): honor enable_precise_embedding_interpolation on the default ViT path
- Fix DeepSeek-V4 mHC combine allocating transients in the NCCL symmetric pool
- Docs
- Python not yet supported