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
- fix(pd): propagate pre-queue aborts to decode
- benchmark: MI300X FP8 speed + accuracy data for MiniMax-M2.7
- [AMD] sgl-kernel: enable gfx1151 (RDNA3.5 / Strix Halo) for single-GPU
- [Kernel] Add fused activation + FP8 quantization JIT kernel for Triton MoE path
- [FP8][MoE] Honor UE8M0 activation scales in Triton MoE
- Let Ampere use the MXFP4 Marlin MoE path
- refactor(kernels): split zero-KV fixup by alignment
- [BugFix] Fix symmetric memory allocation during CUDA graph capture
- [AMD] CI - enable torch compile in AMD CI
- [CI] Enable venv in CI install dep script
- Docs
- Python not yet supported