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
- [Fix] Scope the GLM47 tool grammar to requests that allow tool calls
- [AMD] aiter unified attention: refresh the CUDA-graph page table at page_size 1
- [diffusion] LTX-2.5: balance tile-parallel decode by tile volume (LPT)
- [dLLM] Support per-request temperature, top-p and top-k sampling
- [Bug] Interrupted Mooncake trace download is reused as a complete cache
- [Fix] Do not cache a partial benchmark dataset download
- Fix crash when top_logprobs exceeds vocabulary size
- [AMD] Let the GLM DSA NextN draft declare its own shared-expert fusion architecture
- [Frontend] Parallelize long chat prompt encoding
- [DO NOT MERGE][XPU] Install sglang-kernel-xpu from sgl-kernel-xpu main branch
- Docs
- Python not yet supported