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] GLM detectors: streamed tool-call arguments disagree with non-streaming
- [Fix] step3: parameterless tool calls are dropped, batched calls get mixed up
- fix(modelopt): expand is_layer_excluded for fused and model.-prefixed names
- [NPU]Add NPU test suites for linear attn verify, SMG gRPC mode and disaggregation extra slots.
- perf(attention): adapt TRTLLM MHA scheduling for ragged decode
- fix(observability): restore speculative-decoding spans on the Spec V2 paths
- Cover image-token usage on the generic chat path
- [Docs] Explain unknown tool recovery
- [AMD][DSV4] fp8 unified_kv decode/verify via aiter FlyDSL v4 nm decode
- Fix DeepSeek V3.2/V4 DSML detector stripping whitespace from string params
- Docs
- Python not yet supported