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
- Add B200 NVFP4 MTP deployment to DeepSeek-R1 cookbook recipe
- fix(nixl): prevent read-during-write via atomic temp file rename
- [PP] Carry TP-sharded flag in proxy-tensor metadata to fix #30015
- [Spec] Harden multi-layer EAGLE grammar verification
- fix: do not override SGLANG_FLASHINFER_WORKSPACE_SIZE when user explicitly sets it
- docs: add Top-n-sigma custom logit processor example
- fix(function-call): preserve numeric-looking string arg IDs in step3 detector
- [Feature] Add hits-per-token (HPT) size-aware radix-cache eviction policy
- [Bug] Scheduler event loop blocks on Mamba eviction under large-context requests, causing server hang and process kill
- Skip mamba middle chunks
- Docs
- Python not yet supported