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
- [Perf] mem_cache: Fuse INT8 Mamba checkpoint quantization and restore
- [Feat] scheduler: Add the UniBoost schedule policy
- [Feat] scheduler: Adapt the UniBoost gamma online from the response-time tail
- [Feat] scheduler: Bound UniBoost waits of requests that share a prefix
- [Feat] scheduler: UniBoost decode time-slicing for first-token-starved waiters
- [Perf] [AMD] dsv4: Cut HIP prefill and verify host overhead
- [Fix] scheduler: Clear setwise pooling positions when a request is aborted
- [NPU] a5: fix vl models bug
- [Bug] ModelOpt NVFP4 MoE crashes at warmup with AttributeError 'g1_scale_c' under the default --moe-runner-backend auto on Blackwell
- [Doc] [NVIDIA] qwen3: Add 16 GB consumer GPU (SM89) config tip to the cookbook
- Docs
- Python not yet supported