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] Qwen3.5 prefix-cache reuse changes logprobs with deterministic inference enabled
- Perf [AMD] fusion FlyDSL QR int4 and Add rms norm
- [Fix] quantization: Store --quantization-param-path KV scales the way checkpoint KV scales are stored
- [Fix] constrained: Share one compile among concurrent requests for a grammar key
- [Feature] Accept extra_params on /v1/audio/speech like vLLM-Omni (Qwen3-TTS currently ignores it without an error)
- [Fix] constrained: Fix Outlines jump-forward byte parsing and empty jump helper
- [Fix] kernels: Support OOT fused ops under torch.compile
- [Test] [AMD] do_not_merge: test pr46883
- [Fix] mem-cache: Use indexed operations for Mamba state slots
- [Feat] attention: Add OOT linear-attention backend registration
- Docs
- Python not yet supported