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
- [Feat] openai: support allowed tool subsets in Chat requests
- [Fix] dp-attention: Pad extend host lists out of place so pre-planned DSA metadata keeps its rows
- [Fix] api: Preserve error details across streaming boundaries
- [Feat] PD: Add Mooncake host-only KV staging for decode
- [Feat] [NPU] PD_Disaggreagation: support Mooncake transfer backend
- [Feat] kv-events: Report caller multimodal routing labels as block spans
- [Feat] tracing: Don't trace health checks
- [Feat] metrics: count requests that meet latency SLOs for goodput
- [Fix] anthropic: reject non-string tools[*].type with a 400, not a plain-text 500
- [Doc] [NPU] cookbook: add A3 deployment scenarios to GLM-5.1
- Docs
- Python not yet supported