Sealbook / Open source / Machine learning & data science

vipshop/cache-dit

A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for DiTs.

flux2-kleinparallelismsvdquant

GitHub ↗Website ↗

License & maintenance

Apache-2.0 is a permissive license: free to use commercially with attribution.

Last code push 3 days ago.

Similar projects

	Repository	Stars	Language	License	Activity
1	openclaw/openclawThe AI that really does things. Any OS. Any Platform. The lobster way. 🦞	★ 392.4k	TypeScript	MIT	Active
2	tensorflow/tensorflowAn Open Source Machine Learning Framework for Everyone	★ 201.1k	C++	Apache-2.0	Active
3	AUTOMATIC1111/stable-diffusion-webuiStable Diffusion web UI	★ 165.1k	Python	AGPL-3.0	Slowing
4	Comfy-Org/ComfyUIThe most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the w	★ 138.4k	Python	GPL-3.0	Active
5	openai/whisperRobust Speech Recognition via Large-Scale Weak Supervision	★ 110.8k	Python	MIT	Active
6	pytorch/pytorchTensors and Dynamic neural networks in Python with strong GPU acceleration	★ 104.8k	Python	Other	Active
7	hacksider/Deep-Live-Camreal time face swap and one-click video deepfake with only a single image	★ 97.1k	Python	AGPL-3.0	Active
8	odysseus-dev/odysseusSelf-hosted AI workspace.	★ 93.9k	Python	AGPL-3.0	Active