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] [NVIDIA] attention: Pass explicit backend="trtllm-gen" in trtllm_mla decode
- [Test] deterministic: Isolate backend arguments and fix sampling coverage
- [Test] sampling: Cover hash boundaries and seeded batch invariance
- [RFC] Define per-request speculative decoding opt-out execution semantics
- [Perf] [AMD] mori/Qwen3.5: Send replicated KV heads as pages across P/D attention TP mismatch
- [Fix] disaggregation: fix HiSparse spec PD transfer on PP>1 prefill
- [Feat] benchmark: add rerank benchmark client
- [Fix] [NPU] profiler: :bug: Fix patches and daemon trace parsing
- [Feat] moe: Add Mooncake Elastic EP scale-up support
- [Fix] Apply user stop strings only to the final answer, not the reasoning section
- Docs
- Python not yet supported