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
- [MLX] Fix SchedulerProfilerManager MPS capture mocks
- Report draft and prefill CUDA graph memory in /server_info
- Fix batch-invariant RMSNorm higher-rank shape
- [Feature] Release PyNccl communicator memory in sleep mode
- Fix dp-attention + speculative decoding crashes in flashinfer MLA backend
- Add HashTopK empty output return annotation
- [Bugfix][DSpark] Support speculators-convention checkpoints (gamma+1-wide draft block)
- fix(function_call): strip think tags split across stream chunks in Trinity
- [Bug] DSpark CUDA Graph Capture Fails When --speculative-dspark-block-size Overrides Checkpoint dspark_block_size
- ci: pin jlumbroso/free-disk-space to a full commit SHA
- Docs
- Python not yet supported