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] Reject W4AFP8 MoE group_size != 128 for cutlass chunk_size
- cache offloading for xpu
- [Refactor] Price hybrid SWA pools from a declarative pricing table
- [SM120] Add opt-in NVFP4 sparse-MLA KV cache format for DeepSeek-V4
- [CPU] enable fused_softcap activation kernel
- [Bug] Keep experimental_sgl_trtllm MoE-LoRA reachable for unquantized models
- [LoRA] Run the BF16 trtllm MoE-LoRA path on stock FlashInfer
- [Diffusion] Fuse the Wan VAE conv bias epilogue and tile the RMSNorm+SiLU kernel
- [Feature] Allow caller-provided multimodal cache IDs to avoid repeated hashing and preprocessing
- Clean up KDA track-state test placement and comments from #34820
- Docs
- Python not yet supported