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
- [RFC] Allow prefill CUDA graph bs below chunked_prefill_size under post-capture KV sizing
- [diffusion] attention: Allow disabling sequence masking in SP
- [KV Cache] Add a unified post-hoc sparsity framework with StreamingLLM visibility
- [Fix] HiCache: reclaim redundant host mirrors after storage backup (write_through host-pool starvation)
- [Bug] /v1/responses API fails with 400 when function_call_output output is an array
- [Feature] DSpark Support Prefill TP+CP
- fix(HiSparse): use logical request capacity in disaggregated decode
- [PD] Fix asymmetric MTP metadata buffer mismatch
- [Feature] Add SplitK to CuteDSL SM10X BF16 GEMM
- Warn once when decode batch exceeds the largest captured CUDA graph shape
- Docs
- Python not yet supported