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
- [Bugfix] Stop Kimi-K3 free-text string arguments at their own close marker
- [Bugfix] Keep declared Kimi-K3 properties out of the additionalProperties branch
- [AMD] fix: Read HIP device memory when rocminfo prints no pool sizes
- [AMD][Quark] feat: Accept producer-quantized PTPC FP8 inputs
- [AMD] perf: Fuse Kimi-K3 radix-4 routing, MoE sort and MXFP8 quantization
- [AMD] perf: Add Kimi-K3 MLA gate and query-cache kernels
- [AMD] perf: Add Kimi-K3 KDA group-64 and latent MXFP4 GEMM kernels
- [AMD] perf: Add Kimi-K3 FP8 MoE front and latent tail kernels
- [AMD] perf: Integrate Kimi-K3 ROCm fused kernels into the model
- [AMD] perf: Use FlyDSL FP8 FMHA for MLA prefill on gfx950
- Docs
- Python not yet supported