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
- [Bug] FLA kernels fail to compile on nightly-cu134-20261020: Triton removed tl.make_block_ptr
- [Fix] data_parallel_controller: Fix active ranks update and simplify round-robin dispatch
- [Bug] A silent DP rank leaves /flush_cache waiting without a deadline and blocks subsequent flush calls
- [Perf] comparator: Optimize bundle matching
- [Fix] [NVIDIA] DeepSeek-v4.1: scatter the replay tail before the prefill CP gather with DSpark
- [Fix] [NPU] tests: Prefetch the sgl_eval MMLU archive and pin the Mamba SSM dtype
- [Doc] [NPU] cookbook: add A3 deployment scenario to Qwen3.8
- [Fix] attention: Restore block pointers on Triton 3.9 for FLA kernels
- [Fix] [Intel] attention: Fall back to intel_xpu for deterministic inference
- [Feat] [NPU] quantization: Support static compressed-tensors W8A8
- Docs
- Python not yet supported