A parallelism VAE avoids OOM for high resolution image generation
☆95May 8, 2026Updated 2 months ago
Alternatives and similar repositories for DistVAE
Users that are interested in DistVAE are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆19Nov 18, 2024Updated last year
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆34Nov 29, 2024Updated last year
- Quantized Attention on GPU☆45Nov 22, 2024Updated last year
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,659Jul 14, 2026Updated last week
- ☆192Jan 14, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆427Jul 5, 2025Updated last year
- faster parallel inference of mochi-1 video generation model☆123Feb 25, 2025Updated last year
- Patch convolution to avoid large GPU memory usage of Conv2D☆95Jan 23, 2025Updated last year
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆681May 21, 2026Updated 2 months ago
- A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for DiTs.☆1,234Jul 15, 2026Updated last week
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆58May 3, 2026Updated 2 months ago
- ☆45Oct 15, 2025Updated 9 months ago
- ☆52May 19, 2025Updated last year
- a size profiler for cuda binary☆71Jan 15, 2026Updated 6 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆172Nov 5, 2024Updated last year
- Model Compression Toolbox for Large Language Models and Diffusion Models☆795Aug 14, 2025Updated 11 months ago
- Qwen-Image's DiT inference with TensorRT-10☆21Oct 13, 2025Updated 9 months ago
- [WIP] Better (FP8) attention for Hopper☆33Feb 24, 2025Updated last year
- Agent-native Seedance 2.0 short-film studio: cli for AI, canvas for human☆15Jun 14, 2026Updated last month
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆263Dec 27, 2024Updated last year
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,017Feb 25, 2026Updated 4 months ago
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆727Dec 2, 2024Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆154Dec 4, 2024Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A unified inference and post-training framework for accelerated video generation.☆3,869Updated this week
- ☆82Dec 27, 2024Updated last year
- ☆170Dec 27, 2024Updated last year
- Distributed Compiler based on Triton for Parallel Systems☆1,495Updated this week
- KsanaDiT: High-Performance DiT (Diffusion Transformer) Inference Framework for Video & Image Generation☆62May 13, 2026Updated 2 months ago
- A CUDA kernel for NHWC GroupNorm for PyTorch☆23Nov 15, 2024Updated last year
- ☆37Aug 7, 2025Updated 11 months ago
- [CVPR 2024] DeepCache: Accelerating Diffusion Models for Free☆970Jun 27, 2024Updated 2 years ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆887Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A lightweight design for computation-communication overlap.☆242Jan 20, 2026Updated 6 months ago
- Unofficial extension implementation of Self-Forcing to support I2V && 14B training.☆380Sep 29, 2025Updated 9 months ago
- ☆20Sep 28, 2024Updated last year
- VideoSys: An easy and efficient system for video generation☆2,026Aug 27, 2025Updated 10 months ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆694Jul 4, 2026Updated 2 weeks ago
- Estimate MFU for DeepSeekV3☆26Jan 5, 2025Updated last year
- Combining Teacache with xDiT to Accelerate Visual Generation Models☆33Apr 21, 2025Updated last year