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
- [Spec] Tolerate draft configs that fail to parse during algorithm resolution
- fix(dsv4): support R3 capture and MXFP4 online updates
- [Feature Request] Add pipeline-parallel support to Qwen4-Exp (`qwen4_exp.py`) — four gaps, working reference patches, and an undocumented mHC PP-boundary contract
- [MoE][deepep_v2] Fix ep_scatter_from_psum missing positional args to _fwd_kernel_ep_scatter_2
- [benchmark] Add ascend_bench: config-driven benchmark sweeps with SLA gating for Ascend NPU
- feat(deepep_v2): validate Qwen3.5 MoE for --moe-a2a-backend deepep_v2
- [AMD][gfx950] Restore fused block-scale FP8 projection paths and fix the MHA_ONE_SHOT KV reload
- [BugFix] Require auth on PD bootstrap PUT /route
- [GLM-5.3 Flash] Serving optimizations: KDA/mHC fusion, DSA draft metadata graphs, prefill autotuning
- [Fix] Let parserless xgrammar tool-call tags admit the template's reasoning prefix
- Docs
- Python not yet supported