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
- [Spec] Fix OOB in EAGLE3 draft-extend prefill BCG on multimodal models
- [NPU] Support mxfp4/8 deepep dispatch for 950NPU
- [HiCache][bugfix] Fix cudaGetErrorString TypeError masking cudaHostRegister failures
- Rust TreeCore (v0.5.19) shows e2e regression at concurrency on small dense model
- Honor X-Data-Parallel-Rank on /generate, carry routed_dp_rank through /v1/messages and Responses tool loops
- [Docs] Add Qwen3-Next Ascend NPU deployment to the Cookbook
- [Lint] Reject methods shadowed by a later def in the same class
- [AMD] Add the AgentX Qwen3.5 MXFP4 + MTP tp2 sweep and eval on MI35x
- [Feature] Store DeepSeek-V4.1 C1/C2 Main KV in packed FP4 on Hopper
- [Diffusion][SenseNova] Reduce host-device syncs in denoising
- Docs
- Python not yet supported