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
- [Model] Add deepseek v3 bidirectional embedding
- `batch_is_full` latched during final chunked-prefill pass starves waiting queue until a running request finishes (self-healing variant of #28530 / #22518)
- [Fix] Preserve deterministic DSpark target-verify parity
- Cap anthropic dependency to <1
- [XPU CI] Guardian bot: auto-disable PR on 2-run XPU regression (draft)
- [GDN] Validate FlashInfer Cake CP prefill on Blackwell
- [FlashInfer MLA] Use public CUDA graph plan updates
- Fail fast for MXFP4 MegaMoE/DeepEP on non-SM100 GPUs
- [Bug] 13 tool-call parsers silently delete the message when generation stops at a tool-call open marker
- fix: account native Qwen3.5/3.8 MTP KV layers in target pool sizing
- Docs
- Python not yet supported