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
- Remove 3 labeler globs that match no files
- [flashinfer] Pass window_left at plan time for DFlash verify
- [spec] Reject trtllm_mha for DFlash drafts with non-causal sliding layers
- refactor: decouple TRTLLMHAAttnBackend from FlashInferAttnBackend
- [Tracking] Host allocator: page-aligned allocation with host-side bookkeeping
- feat(npu): support Kimi K3 PCP with FLA affine states
- [Bug] Anthropic /v1/messages drops PD bootstrap fields during AnthropicMessagesRequest → ChatCompletionRequest conversion
- [LMCache] Support MLA/DSA dual-buffer KV cache in LMCache connector
- [NIXL] Fix O_DIRECT alignment and batch chunking for DSA indexer pool
- Add SM100 NVFP4 KV cache support for GLM-5.2 DSA
- Docs
- Python not yet supported