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 short standalone DeepSeek-VL2 image embeddings
- Cut repeated setup from DeepSeek-VL2 multi-image requests
- Add nightly AIME25 test for DeepSeek-V4-Pro on B200
- Fix memory consumption when loading Mistral Medium 3.5
- fix: return cached_tokens and reasoning_tokens in sgl-model-gateway grpc usage
- Support stop parameter for mtp
- Fix GLM4 MoE Lite shared expert TP flag
- [CI] runner-utilization: queue-wait-over-time + running/queued charts
- [SPEC] feat: adaptive spec anti-oscillation
- fix: guard metrics scrapes from starving health checks
- Docs
- Python not yet supported