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] [NVIDIA] speculative: Move the host work between Qwen3.5 MTP decode graphs into the graphs (1/2)
- [Fix] patch_torch: rebuild CUDA tensors in processes without the reductions patch
- [Fix] spec: init the active attention backend for eager IDLE batches
- [Fix] [AMD] offloader: keep is_shuffled on device copies of offloaded weights
- [Sglang-Diffusion-XPU] Add support for sage_attn
- [Fix] [AMD] MoE: Preserve CT FP8 Triton layout and reduction dimensions
- Reenable ngram corpus testcase for XPU
- [RFC] Expose allocator-issued page generations to external linkers
- [Perf] attention: avoid concatenating MLA queries for zigzag CP
- [Feature] hicache: support DCP with EAGLE/MTP speculative decoding
- Docs
- Python not yet supported