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
- [Feature] Streamed restore: chunked materialization for oversized storage hits in buffer_only HiCache mode
- [Bug] InternVL with a GPT-OSS backbone fails to load weights (UnboundLocalError: stacked_params_mapping)
- [Bug] [XPU] DSpark drafts all rejected under full decode graph with TP=2: TP ranks diverge on draft graph replay
- [Feat] metrics: expose detokenizer router processing time
- [Fix] disaggregation: drop STAGING_RSP for chunks this engine never requested
- [Chore] [AMD] monokernels: Pin sgl-amd-mono at plugin main with the GLM and MiniMax-M3 specs
- [Chore] ci: Update test est_time values
- [Feat] ngram: let each request draft from its own prompt
- [Fix] flashinfer: honor DECODER_BIDIRECTIONAL in extend attention
- [Fix] hicache/hf3fs: Prevent duplicate page reservations
- Docs
- Python not yet supported