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
- [CI] comfyui: Add a workflow validator and e2e harness for the shipped workflows
- [diffusion] comfyui: run LTX-2.5 / LTX-2.3 in SGLD integrated mode
- [Fix] Preserve Qwen3-Coder tag examples in streaming text
- [Bug] PP>1 (GLM-5.3/DSA): intermittent runtime crash in RotaryEmbedding.forward_cuda — query.view(positions.size(0), -1, head_size) with a shorter positions tensor
- [Feat] comfyui: Add an image-to-3D node for the Hunyuan3D server
- Pin pip CUDA JIT toolchain to the CUDA minor required by torch
- [Feature] Add public, non-fatal weight update refusal
- [Feat] kimi_k3: Run the EAGLE3 MLA draft under DCP with a physical draft KV pool
- [Perf] mem_cache: Batch the KV release of requests that finish in the same step
- [Feature] Add public weight offloader factory and post-load hook
- Docs
- Python not yet supported