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
- [Quantization][RL] Support Online Blockwise FP8 Quantization
- [Tracking] CI Test Failures and Fixes
- [AMD][AITER attention backend] Adjust `available_bytes` in `KVCacheConfigurator` to avoid OOMs in AITER attention backend buffers allocation
- Onboard voyage-4-nano
- feat: load / save model weights from / to mooncake store
- [CI]: Add hybrid model testing in hicache ci
- [Perf & Feat] Add deepseek32 topk opt : Introduction to the ultra low latency attention
- [diffusion] Add cancellation for async diffusion video jobs
- [RFC] Refactor weight loading code
- Refactor and optimize Gemma4 attention QKV proj and norm
- Docs
- Python not yet supported