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
- [Doc] cookbook: add Ascend NPU deployment for Qwen3
- SGLANG_JIT_DEEPGEMM_FAST_WARMUP on DeepSeek-V4.1: 3-5x faster cold start, no runtime degradation detectable at chunked-prefill 16384
- [Fix] model-loader: Honor explicit weight loaders for object-store models and drafts
- [Fix] logging: Bound token-ID decoding in partial request logs
- [Feat] tracing: Attribute prefix checkpoint CPU time to requests
- [Fix] scheduler: reserve SPF capacity against both token budgets
- [Feat] scheduler: Add max-queued-tokens for request management
- [Fix] deepseek_v41: track image work after cancellation
- [Fix] benchmark: Add offline guidance for random datasets
- [Fix] scheduler: Do not request input logprobs again when re-prefilling a retracted request
- Docs
- Python not yet supported