{"library":"cache-dit","type":"library","category":null,"description":"Cache-DiT is a PyTorch-native inference engine designed for Diffusion Transformers (DiTs). It provides hybrid cache acceleration (DBCache, TaylorSeer, SCM), comprehensive parallelism optimizations (Context, Tensor, 2D/3D), and low-bit quantization (FP8, INT8, INT4). The library integrates seamlessly with Hugging Face Diffusers, SGLang Diffusion, vLLM-Omni, and ComfyUI to deliver significant speedups for image and video generation. Currently at version 1.3.5, it maintains an active release cadence with frequent updates and hotfixes.","language":"python","status":"active","version":"1.3.5","tags":["pytorch","inference","quantization","dit","diffusion","parallelism","cache","acceleration","gpu","huggingface-diffusers","comfyui"],"last_verified":"Sun May 24","install":[{"cmd":"pip install -U cache-dit","imports":["import cache_dit","from cache_dit import DBCacheConfig, ParallelismConfig, QuantizeConfig","from cache_dit import DBCacheConfig, ParallelismConfig, QuantizeConfig","from cache_dit import DBCacheConfig, ParallelismConfig, QuantizeConfig","cache_dit.enable_cache(pipeline_instance)"]}],"homepage":null,"github":"https://github.com/vipshop/cache-dit","docs":null,"changelog":null,"pypi":"https://pypi.org/project/cache-dit/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":40,"avg_install_s":84.1,"avg_import_s":19.83,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/cache-dit/compatibility"}}