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
- docs(cookbook): fix broken DeepSeek-V3.2 link in Jina reranker page
- [Docs] Add weight cache flags to the server args table
- Guard get_masked_input_and_mask torch.compile against XPU, not just NPU
- Allow chunk-only prefill/decode interval protection
- [Docs] Add four HiCache flags to the server arguments table
- Add JIT CUDA kernels for NewGELU and QuickGELU
- [Spec] Preserve genuine token 0 leaves in NGRAM corpus merges
- [Spec] Don't charge FROZEN_KV_MTP draft layers against the target KV pool
- [1/N] [DSV4.1] Add packed FP4 Main KV storage for Hopper.
- [2/N] [DSV4.1] Add SM90 attention for packed FP4 Main KV.
- Docs
- Python not yet supported