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
- [Feature] Support single-worker Replay simulation on Apple Silicon macOS
- [Fix] [AMD] kimi-k3: Give AITER's A16W4 SiTU MoE the separated w13 la…
- [Perf] attention: Let SM12x FA4 split KV outside the architecture decode policy
- [Fix] RL: Flush cache after partial distributed weight update
- [Fix] Keep tokenizers parallelism on for multimodal models
- [ROCm][AMD] Qwen3.8-27B gfx950 / MI355X Performance Optimization (SGLang)
- [CI] labeler: cover the rust sglang-mm and sglang-server crates
- [Fix] hicache: Report L3 prefetch tokens already cached during the read
- [Perf] [AMD] deepseek-v4.1: Opt into Mega-mHC on decode and verify steps
- [Fix] cohere_command4: Strip an echoed think-start and keep same-chunk answers in streaming
- Docs
- Python not yet supported