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] hicache: Re-back up hit host prefixes missing from L3 storage
- [Bug] ComfyUI SGLD loader: Fun ControlNet on Qwen-Image 2.1 fails with AttributeError
- [Perf] dsv41-flash: Add FP8 DeepGEMM prefill scoring on Hopper
- [Perf] dsv41-flash: Increase the prefill Indexer score tile budget
- [Perf] dsv41-flash: Reuse paged Indexer key tiles during verification
- [Perf] dsv41-flash: Fuse Hopper prefill candidate selection and writeback
- [Fix] disaggregation: Keep a decode request without bootstrap_host from crashing the scheduler
- [Feat] cache: Support plain MHA direct-linker views
- [Feat] dLLM: Add HierarchyBlock decoding for Fast-dVLM (text, radix cache on)
- [Fix] lmcache: wait for pending loads before ending sessions
- Docs
- Python not yet supported