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] dsv41: Surface malformed tool output as explicit API errors
- [Feat] DSv4.1: Run deepep_v2 on DeepEP 2.5 with FP4 experts and DSpark drafts
- test some test cases
- [CI] [AMD] stage-b: Run the scheduled mi35x 1-GPU small suite on the 8-GPU pool
- [Fix] hicache: Reject v1-only storage backends at attach time on multi-pool cache stacks
- fix(humming): adapt integration to kernels 0.1.18
- [Feat] Inkling: upgrade tml-renderers to 0.2.1
- [Fix] scheduler: Dedupe shared prefixes in shortest-first order under SPF
- [Perf] [NVIDIA] deepseek_v4: Write wo_a output token-major when a rank holds all 8 groups
- [Perf] mhc: Split hc_combine_norm_mxfp8 rows by batch size and zero padding scales in the kernel
- Docs
- Python not yet supported