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
- [Perf] deepseek-v4.1: Replay the breakable prefill CUDA graph at any context length
- chore: update CI test est_time values
- :construction: [WIP][llm][npu][quant] Add W4A8 MXFP quantization support for Qwen3.5 MoE on Ascend NPU
- :construction: [WIP][llm][npu] Split mixed chunked-prefill FIA into prefill/decode calls on Ascend 950
- [Spec] Fix NGRAM over-sampling token 0 from padded draft siblings
- mhc_fused_post_pre crashes at graph capture: DeepGemm tf32_hc_prenorm_gemm API mismatch (n_splits-shaped output no longer accepted)
- [Spec] Add aux hidden-state capture for Granite and GraniteMoe targets
- [Diffusion] MiniMax H3: allow the AdaLN cache with a quantized DiT
- [NPU] Initialize padded vision attention outputs to prevent MiniCPM NaNs
- [Fix] replay_ssm: Reject unflushed ReplaySSM cache checkpoints
- Docs
- Python not yet supported