A PyTorch inference engine for Diffusion Transformers (DiTs) that adds caching, parallelism, quantization and CPU offload on top of Diffusers.
1.3K92PythonApache-2.0Updated 7 hours ago
#parallelism
Curated GitHub repositories related to parallelism, with AI summaries and key stats.
A PyTorch inference engine for Diffusion Transformers (DiTs) that adds caching, parallelism, quantization and CPU offload on top of Diffusers.