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
- Prevent full CUDA-graph serving from corrupting MHC and DSA tensors
- K3 PD disaggregation
- [Speculative] Bound request KV for uniform sliding-window DFlash drafts
- [Test] Fix MiniMax sparse FP8 attention GEMM imports
- [Feature] Batch-level hybrid speculative decoding
- [Bug] /v1/responses silently drops prompt_cache_key instead of applying it to radix-cache identity
- [Bug] Honor prompt_cache_key on /v1/responses
- fix(memory): skip speculative Mamba verify budget on PD prefill
- [Benchmark] Add a lightweight online stress suite
- [Bug] DeepSeek-V4-Flash-0731 fails to load on v0.5.17/v0.5.18: AssertionError: Hidden size mismatch in the mxfp4 MoE path (works on main)
- Docs
- Python not yet supported