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
- trace: propagate W3C trace context through Mooncake PD boundary
- [Feature] dflash2 speculative decoding support pipeline parallelism
- fix(BCG dp): align prefill CUDA graph capture sizes to attn_tp_size under DP attention
- fix(test): update shared-KV GQA coverage
- test(perf): add AMD score API latency bounds
- [AMD] Add ROCm MegaMoE path via AITER MegaMoEV2
- [openai][bench] Keep buffered decode steps observable so tool-call runs report real ITL/TPOT
- perf(deep-gemm): specialize static N and K dimensions for dense GEMMs
- Fix string-valued numeric constraints in tool schemas
- [Bug] qwen3.6-35b-a3b repeat bug
- Docs
- Python not yet supported