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
- Back origin_input_ids and output_ids with a single TokenBuffer
- [Feature] Decode context parallelism (DCP) for DSA models (DeepSeek V3.2, GLM-5.x)
- feat(diffusion): add OmniDreams autoregressive video world model
- [server_args][deepep] Auto mem reservation + capacity auto-tuning for DeepEP+DP serving
- Support SM100 and SM103 TP8 FlashInfer sequence parallelism for Llama 3.1 70B
- [KDA] Integrate cuLA KDA Prefill Backend
- feat: flush decode KV only for prefill reads on extend requests
- [Kernel] feat: add flexprefill for long-context
- Submit use case code for the tensor_dumps, model_override, and Metric…
- [Kimi] trtllm_mla: serve varlen absorbed MLA under captured prefill CUDA graphs (fixes #32655)
- Docs
- Python not yet supported