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
- [CP] Support GLM-5.3-Flash colocated prefill CP and decode attention TP with DFlash2/MTP
- [Kernel] Add H800 W8A8 block-FP8 GEMM tuning configs
- [HiCache] Parallel, THP-backed host pool allocation (opt-in)
- [Bug] qwen_vl: literal "<image>" in message text aborts requests with 500 "Mismatch: More IMAGE tokens found than corresponding data provided"
- [NPU] cover constrained JSON whitespace limits
- [Spec] Capture the prefill CUDA graph for DeepSeek-style NextN drafts
- [AMD][V4.1] Mono kernel framework (--layer-backend mono) and DeepSeek-V4.1 decode layers
- [Bug] GraniteMoE can't load with --moe-runner-backend flashinfer_trtllm (routing_method_type is None)
- [XPU] Upgrade oneAPI base image to 2026.1.3
- [PD] Add opt-in cross-request Mooncake KV batching
- Docs
- Python not yet supported