thu-nics / DiTFastAttn
☆112Updated 2 months ago
Alternatives and similar repositories for DiTFastAttn:
Users that are interested in DiTFastAttn are comparing it to the libraries listed below
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆82Updated 5 months ago
- Accelerating Diffusion Transformers with Token-wise Feature Caching☆31Updated last month
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆116Updated last month
- 📚 Collection of awesome generation acceleration resources.☆63Updated this week
- ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆37Updated 3 months ago
- A parallelism VAE avoids OOM for high resolution image generation☆44Updated 2 months ago
- [CVPR 2024 Highlight] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Mo…☆57Updated 4 months ago
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆31Updated 5 months ago
- PyTorch code for Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers☆36Updated 3 months ago
- This is the official PyTorch implementation of "ZipAR: Accelerating Autoregressive Image Generation through Spatial Locality"☆35Updated last week
- Patch convolution to avoid large GPU memory usage of Conv2D☆79Updated 6 months ago
- Implementation of Post-training Quantization on Diffusion Models (CVPR 2023)☆125Updated last year
- [ICLR 2024 Spotlight] This is the official PyTorch implementation of "EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Di…☆50Updated 6 months ago
- [ECCV24] MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization☆32Updated 3 weeks ago
- TinyFusion: Diffusion Transformers Learned Shallow☆67Updated last week
- VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation☆177Updated last month
- [NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.☆119Updated 2 months ago
- SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training☆162Updated last month
- QuEST: Efficient Finetuning for Low-bit Diffusion Models☆35Updated this week
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆22Updated 2 weeks ago
- A light-weight and high-efficient training framework for accelerating diffusion tasks.☆42Updated 3 months ago
- Curated list of methods that focuses on improving the efficiency of diffusion models☆32Updated 5 months ago
- The official implementation of PTQD: Accurate Post-Training Quantization for Diffusion Models☆89Updated 9 months ago
- [NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification☆14Updated 4 months ago
- ☆56Updated 2 weeks ago
- CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient☆73Updated 2 weeks ago
- [WIP] Context parallel attention that works with torch.compile☆59Updated this week
- This is a repo to track the latest autoregressive visual generation papers.☆71Updated last week
- Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference" proposed by Pekin…☆61Updated last month
- HART: Efficient Visual Generation with Hybrid Autoregressive Transformer☆380Updated 2 months ago