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
- feat: configure abort dispatch window
- [CI] [AMD] deps: Install openai 2.8.0 in AMD CI for the Responses API
- [Doc] diffusion: add Strix Halo (Radeon 8060S) recipe for Qwen-Image 2.1
- [Perf] spec: Avoid blocking H2D for MRoPE delta in spec decode
- [Fix] hicache: Fix MooncakeStore None storage_config and address validation
- [Bug] FlashInfer `cascade` module JIT-compiles inside the first prefixed request (~4.5 s) on pip installs
- [Bug] Weight updates silently load the target's weights into a DFLASH draft; `update_weights_from_disk` has no `selector` to prevent it
- [Feat] [AMD] HiCache: page-striped host tier for DSv4
- [Feat] multimodal: Add configurable hash algorithm for CPU multimodal features
- [Perf] Cache tool-schema meta-validation across requests
- Docs
- Python not yet supported