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
- A retracted + re-prefilled request restarts its sampling-penalty and `min_new_tokens` history from zero, silently changing its output
- [Perf] deepseek-v4.1: Use reduce-scatter for CP MoE output
- [Fix] disagg: Defer aborted prefill release until source reads drain
- [Fix] quantization: Preserve CT MoE zero-point channel order
- [Perf] diffusion: Enable verified eager LN fusion for SANA-Video
- [Fix] [AMD] attention: default consumer RDNA to Triton attention
- [Fix] disaggregation: Bind the DCP pack thread to the pack buffer's device
- [Doc] install: Explain Python 3.13 Outlines build requirement
- [Perf] qwen: Add experimental L2 weight prefetching around TP AllReduce
- [Fix] attention: Keep fused RoPE KV writes off DCP layouts
- Docs
- Python not yet supported