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
- [DeepEP] Use static FP8 communication for W4AFP8 normal dispatch
- auto_tune: implement sglang.auto_tune CLI for MoE kernel tuning (subtask 1 of #13363)
- fix(moe): narrow global expert IDs using the built runner
- Fix DP-aware routing for OpenAI Responses API
- Add distributed exact prompt Top-N logprobs
- Add perf and acc test for CPU models for nightly
- [Bugfix] Bound SGLANG_PORT search to valid TCP range
- [SM120] dspark: widen SWA index width to an instantiated sparse-MLA shape
- [PD] Batch final DSV4 SWA transfer
- fix(dsa): use int64 page offsets in index buffer accessors
- Docs
- Python not yet supported