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
- [KDA] Defer accepted-state materialization for SM90 Triton verify
- [Bug] SM120 grouped FP8 DeepGEMM weight preparation skips UE8M0 requantization
- [Bugfix] Infer the draft path for Qwen3.5 bundled MTP
- fix(openai): honor include_reasoning=false on chat completions
- [core] Make SWA sizing policy explicit and separate pool costs
- [Kernel] Add fused MoE Triton down-projection config for Qwen3.8-Flash-Next FP8 on NVIDIA H200 NVL (TP2+EP2)
- [Tokenizer] Reduce Kimi-K3 encoding overhead for tool-call-heavy requests
- [Bug] Client disconnect during active request crashes entire engine (uncaught asyncio.CancelledError bypasses except Exception)
- [MLX] Build FutureMap on the req_to_token_pool device, not the scheduler device
- [MLX] Init mamba grid attributes in MlxAuxiliaryStateComponent
- Docs
- Python not yet supported