There are 0 repository under torch-compile topic.
End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
Minimal repository to demonstrate fast LoRA inference with Flux family of models.
Leveraging torch.compile to accelerate cross-encoder inference
⚡ Boost torch.compile performance and cache efficiency with this compact ComfyUI node set, designed for seamless integration with WanVideo Cython Model Loader.
🚀 2-4x faster PyTorch training with one line of code. Beats torch.compile by 79%. Zero config, automatic hardware optimization for T4/V100/A100/H100 GPUs.