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
- [Intel GPU] Add opt-in decode graph capture widths for DSV4 on XPU
- [feat][NPU] Add not needs_cpu_seq_lens for dsa modules
- [BCG][DSV4-Flash][CP] Support DeepSeek V4 prefill with interleave CP and breakable CUDA graphs
- [MoE] Improve NCCL EP LL decode with single-compute-stream TBO
- [Fix] Preserve sampler customized_info across PD disaggregation
- [Feature][DSv4.1] Tracking: every backend's two-level candidate indexer behind CandidateIndexer
- [Feature] Cascade attention kernels
- [WIP][Quantization] fix: fix gguf moe model inference
- Emem qwen3 next (After https://github.com/sgl-project/sglang/pull/13581)
- Optimize multimodal feature transfer using Shared Memory
- Docs
- Python not yet supported