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
- [XPU][MoE] Enable FP8 MoE dispatch across FP8 quantization methods
- [XPU][MoE] Align FP8 and BF16 MoE expert weights to column-major in ostprocess
- fix(kimi-k3): use int64 attn-residual row indices
- [Bugfix] Escape literal paths when discovering profile traces
- [CUDA graph] Support a persistent pool for shared graph state
- [Benchmark] Isolate fast-prepare caches from measured token counts
- [NPU]glm5.2 optim origin dual stream
- [ROCm][DSV4] Support row-strided inputs in C4 v2 compression
- [ROCm][DSV4] Add opt-in C4 compressor GEMM fusion
- [Kernel][FP8] Fuse SiluAndMul with static FP8 quantization
- Docs
- Python not yet supported