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
- Validate PD top logprobs metadata limit
- fix(bench): honor CUDA decode profiling step limits
- fix(rocm): don't attempt CUDA IPC handle creation on ROCm tensors; document the pitfall
- Fix HashTopK empty output shapes
- [3/3] [EAGLE] perf: Remove redundant draft capture input staging
- [Security] Add opt-in chat content sanitization
- [Lora]Fix GDN LoRA mapping for fused Qwen3.5 projections
- A fix for DSA models without q_lora_rank
- [XPU] Add full backend support for prefill graph
- [Bug] GPT-OSS + require_reasoning + json_schema emits malformed Harmony without Role and Channel
- Docs
- Python not yet supported