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
- [Fix] tp_worker: Seed each attention-DP group with its own random stream
- [Fix] runtime: Sync FlashInfer autotune tactics across attention-DP groups
- [Test] [NPU] return-aux-hidden-states: Add NPU e2e testTest npu return aux hidden states
- [Fix] glm5: support interleave CP prefill BCG row boundaries
- [Feat] [NPU] runtime: prewarm the native pinned-host allocator
- [Feat] hicache: trace per-request storage prefetch phases
- [Feat] hicache: expose pending work and backup outcome metrics
- [Feature] Add per-request skip_detokenize option to sglang.api.v1.GenerateRequest
- [Feature] Honor chat-template stop strings when ChatCompletionRequest carries input_ids
- [RFC] Integrate MindIE-SD as an Acceleration Library for SGLang Diffusion
- Docs
- Python not yet supported