1 dépôt
Awesome GitHub RepositoriesInference Optimizations
Techniques specifically designed to reduce the runtime latency and memory footprint of diffusion models.
Distinct from Diffusion Models: Covers the holistic application of quantization and distillation for inference, distinct from general diffusion model interfaces.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Inference Optimizations. Refine with filters or upvote what's useful.
Awesome Inference Optimizations GitHub Repositories
Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
- thu-ml/turbodiffusion
thu-ml/TurboDiffusion
3,339Voir sur GitHubTurboDiffusion is a video diffusion inference engine and generator designed to create high-resolution videos from text prompts and images. It provides a runtime environment for executing optimized diffusion model checkpoints with a focus on reducing latency and GPU memory usage. The project features a specialized training framework for aligning sparse-linear attention models with pretrained full-attention models. This system includes capabilities for sparse attention parameter merging and sparse-linear model alignment to reduce computational costs during inference while maintaining output qua
Reduces inference time and GPU memory usage through quantization, timestep distillation, and attention acceleration.
Pythonai-infraconsistency-modeldiffusion-models
