IronMan's repositories
Awesome-Vision-Knowledge-Distillation
Awesome Knowledge-Distillation for CV
Awesome-Efficient-Diffusion-Models
Paper survey of efficient computation for large scale models.
Auto-Prox-AAAI24
Auto-Prox-AAAI24
res-adapter
Official implementation of "ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models".
Switch-DiT
Official pytorch implementation of "Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts"
AdaGP
Official Repo for Adaptive Global Pruning of LLMs
APQ-DM
This is the official pytorch implementation for the paper: Towards Accurate Post-training Quantization for Diffusion Models.(CVPR24)
Awesome-Efficient-LLM
A curated list for Efficient Large Language Models
DiffusionNAG
Official PyTorch implementation of "DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models" (ICLR 2024)
EfficientDM
[ICLR 2024 Spotlight] This is the official PyTorch implementation of "EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models"
FouriScale
Official implementation of FouriScale
FRDiff
FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models
LMM-Pruning
A simple and effective LMM pruning approach.
loretta
[NAACL 24] LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models
MACE
[CVPR 2024] "MACE: Mass Concept Erasure in Diffusion Models" (Official Implementation)
PAE
[CVPR 2024] Dynamic Prompt Optimizing for Text-to-Image Generation
peta
Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"
PlainMamba
PlainMamba: Improving Non-hierarchical Mamba in Visual Recognition
shortened-llm
Compressed LLMs for Efficient Text Generation [ICLR'24 Workshop]
SimDA
[CVPR 2024] SimDA: Simple Diffusion Adapter for Efficient Video Generation
T-GATE
Accelerating Text-to-Image Diffusion Model for Free
TFMQ-DM
[CVPR 2024] TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models
VideoMamba
VideoMamba: State Space Model for Efficient Video Understanding
VidToMe
Official Pytorch Implementation for "VidToMe: Video Token Merging for Zero-Shot Video Editing" (CVPR 2024)
zigma
The official implementation of "ZigMa: A DiT-Style Mamba-based Diffusion Model