RiseAI-Sys / ParaVAELinks
Distributed parallel 3D-Causal-VAE for efficient training and inference
☆31Updated 2 weeks ago
Alternatives and similar repositories for ParaVAE
Users that are interested in ParaVAE are comparing it to the libraries listed below
Sorting:
- A Unified Cache Acceleration Toolbox for 🤗Diffusers: FLUX.1, Qwen-Image-Edit, Qwen-Image, Wan2.1/2.2, etc.☆244Updated this week
- High performance inference engine for diffusion models☆81Updated last month
- ☆173Updated 7 months ago
- Triton based sparse quantization attention kernel collection☆38Updated last week
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆389Updated 2 weeks ago
- Code for Draft Attention☆90Updated 3 months ago
- A sparse attention kernel supporting mix sparse patterns☆291Updated 6 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆116Updated 5 months ago
- To pioneer training long-context multi-modal transformer models☆45Updated 3 weeks ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆495Updated this week
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆172Updated last week
- Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation☆16Updated 2 months ago
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆420Updated last week
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]☆32Updated 3 weeks ago
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.☆704Updated 3 weeks ago
- A parallelism VAE avoids OOM for high resolution image generation☆76Updated last month
- flash attention tutorial written in python, triton, cuda, cutlass☆415Updated 3 months ago
- [NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification☆25Updated 5 months ago
- [CVPR 2025] Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers☆59Updated last year
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆41Updated 2 months ago
- Patch convolution to avoid large GPU memory usage of Conv2D☆92Updated 7 months ago
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆159Updated last month
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆36Updated last month
- This is the official PyTorch implementation of "Video-BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generatio…☆23Updated 2 weeks ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆234Updated 3 weeks ago
- Efficient 2:4 sparse training algorithms and implementations☆56Updated 8 months ago
- PyTorch implementation of PTQ4DiT https://arxiv.org/abs/2405.16005☆32Updated 9 months ago
- [NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.☆165Updated 11 months ago
- Official implementation of the ICLR 2024 paper AffineQuant☆26Updated last year
- DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing (WACV 2025)☆11Updated 9 months ago