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] sgl-router: Index prefix-cache depths by worker URL
- [Test] [NPU] qwen3.6-27b: enable expandable_segments for 1080p perf case
- [Fix] deepseek: Merge per-tensor q_a/kv_a scales into the fused projection
- [CI] NPU: Narrow NPU PR test to perf-16 and add host-resource sampling
- [Bug] /v1/responses: late system/developer messages are moved to the top of the prompt, so the prefix cache misses every turn
- [Quantization] Fix vision layer ignore-list renaming for Gemma 3 / Mistral 3
- L3 cache run
- [Perf] [AMD] batch-invariant: Faster small-M launch for the segmented bf16 matmul on gfx950
- [CI] [NPU] ci: Cap acc-2 nightly partition concurrency
- [Fix] kernels/jit: Honor the unified cache root
- Docs
- Python not yet supported