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
- [Fix] Load Hunyuan attention sinks using projection placement
- [sched] Test that the admission re-match records num_matched_prefix_tokens
- Detokenizer return-path fanout performs one IPC send per request
- [NPU]Support NPU DSV4 breakable prefill graphs
- [MLX] Fix --disable-overlap-schedule crash: match device when stashing relay payloads
- Feat/qwen4 exp ascend a2
- Enable SM120 GLM DSA NVFP4 KV cache with FlashInfer
- [Bug][function_call] Keep Qwen3Coder string null and invalid booleans
- [Bug][function_call] Keep GLM string arguments as raw text
- fix(openai): preserve zero cached tokens when cache reporting is enabled
- Docs
- Python not yet supported