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
- Bound DSpark rejection sampling workspace
- [function_call] Make streaming tool-call parsing agree with non-streaming
- Drop null `required`/`properties` in tool schema normalization
- [Feature] Support partial-page prefix reuse in RadixCache
- Preserve incomplete tool-call markers
- Improving Agentic RL Rollout Inference Efficiency with Uniboost Scheduler Policy
- [mem_cache] test: ratchet the allocator and pool_host layout
- [reasoning] Strip an echoed think-start token when streaming
- [Feature] [RFC] Same-GPU model replicas with managed CUDA MPS and a shared KV pool
- fix(security): block SafeUnpickler builtins gadget chain
- Docs
- Python not yet supported