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
- [HiCache] Skip mamba radix caching instead of asserting when no slot can be evicted
- [Bug] False assertions exist in the mmlu test of PR:24689
- [LPLB] Make the IPM solver CUDA-graph safe, and halve its shared memory
- [SM100] Add optimized Q8KV8 sparse prefill for DeepSeek-V4-Flash
- [PD] Release PP prefill responses before ring consensus
- [CPU][Spec] Enable DFLASH speculative decoding on Xeon (intel_amx)
- [AMD] Add dense NVFP4 support for gfx1201
- [Intel] [XPU] Restore XPU MHC dispatch
- [OpenAI] Honor explicit --chat-template over built-in chat encoders; force reasoning for hardcoded-<think> templates
- [NPU]support features --enable-int8-mamba-checkpoint
- Docs
- Python not yet supported