vipshop/cache-dit

Health v2 · maintenance only

Adoption not part of the score

1267 stars · 80 forks observed · 2026-09-03

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Cache-DiT is a PyTorch-native inference engine that accelerates Diffusion Transformer (DiT) models with hybrid caching, parallelism, quantization, and CPU offload. It is built on Hugging Face Diffusers and supports 40+ DiT pipeline families across NVIDIA, AMD, and Ascend hardware.

Use cases

• speed up diffusion transformer inference
• accelerate flux image generation with caching
• run DiT models with context parallelism
• quantize diffusion models for faster inference
• offload diffusion model weights to CPU to fit in VRAM
• integrate DiT acceleration into ComfyUI or vLLM pipelines

When to choose

• you use Diffusers DiT pipelines and need faster inference without changing models
• you need multi-GPU parallelism (context/tensor/2D/3D) for diffusion workloads
• you want cache, quantization, and offload combined in one library

When to avoid

• you need to train or fine-tune diffusion models rather than run inference
• your models are not DiT-based or not supported by Diffusers
• you need a serving engine with its own API server rather than a library

Facets

library · maturity active

llm-inference machine-learning gpu-computing caching deep-learning image-processing gpu-computing machine-learning python windows diffusion-transformers dit diffusers inference-acceleration quantization cpu-offload context-parallelism tensor-parallelism svdquant video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="vipshop/cache-dit")