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(moe): narrow global expert IDs using the built runner
- Fix DP-aware routing for OpenAI Responses API
- Add perf and acc test for CPU models for nightly
- [SM120] dspark: widen SWA index width to an instantiated sparse-MLA shape
- fix(dsa): use int64 page offsets in index buffer accessors
- [NPU] [DOC] Add Kimi-K3 deployment tutorial on Ascend NPU
- perf(moe): add RTX 5080 Granite FP8 Triton config
- [Doc] Add SGLang ecosystem section to README
- fix(deepseek_v2): don't coerce unscaled MLA models onto deepseek_yarn
- [Bug] macOS: shared-memory names can exceed the 31-char POSIX limit, deadlocking `in_the_same_node_as` with no error output
- Docs
- Python not yet supported