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] modelopt: Load serialized NVFP4 experts of hybrid FP8+NVFP4 checkpoints under modelopt_fp4
- [Perf] [NPU] gdn: Enable direct state-pool I/O for prefill
- [Fix] Return HTTP 400 for /v1/responses streams rejected before the first chunk
- TTFT:only prefill
- [Feat] [Intel] HiCache: Support unified-memory HiCache on XPU
- [Feat] [Intel] glm4: Enable GLM4-series CPU inference
- [Feat] [NVIDIA] kimi_k3: Add experimental TP8 specialized decode
- [WIP][Feat] [NPU] Support Jet-Nemotron inference on Ascend NPU
- [Fix] sampling: Apply additive penalties before repetition scaling
- [Perf] parser: Avoid O(N^2) buffer copies and scans in BaseReasoningFormatDetector streaming
- Docs
- Python not yet supported