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
- [SM120] Field report: DeepSeek-V4.1-Flash in production on 8x RTX PRO 6000 (PCIe, no NVLink) - working config, measured throughput, rejected topologies
- [AMD] Eliminate remaining gfx95 FP8 scale relayout copies
- [Bugfix] Qwen 2.5 detector: keep every call and its arguments at end of stream
- Optimize MiMo-V2 router GEMM with the HPC-Ops bf16xfp32 kernel
- [IPC] Send encoded messages without copying
- [SUPA] Add Biren SUPA device detection and SRT platform support
- [Feature] Support bitsandbytes in QWen2 VL
- enabling device auto detection for cuda/cpu/intel-gpu/rocm in UT test
- Add post_load_weights for ShardedStateLoader
- [Feature] Implement Image Number Limitation for Image Processors
- Docs
- Python not yet supported