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
- [Bug] Qwen3.8-27B scores depend on batch shape and can change borderline decisions (FP8 and BF16)
- [NPU] 修复 MLA EAGLE3 的张量并行特征汇聚
- [NPU] Qwen3-ASR compiled decode graph capture fails even with CPU offload disabled
- [npu] support ep allgather
- [Scheduler] Filter finished requests out of running_batch on the non-mixed-chunk prefill path
- [VLM][MM refactor 5/6] Add a token-space strategy for Qwen VL models
- [VLM][MM refactor 6/6] Enable token-space processing at startup with parity tests
- [Feature] [RFC] SGLang Engine Initialization Snapshots: Reusing Initialized State for Faster Startup
- [Bugfix] Preserve routed expert history across KV retraction
- support prefill-complete on npu
- Docs
- Python not yet supported