A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for DiTs.
☆1,262Aug 31, 2026Updated this week
Alternatives and similar repositories for cache-dit
Users that are interested in cache-dit are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆590Jun 13, 2026Updated 2 months ago
- A unified inference and post-training framework for accelerated video generation.☆4,235Updated this week
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,368Jun 8, 2025Updated last year
- Lightweight Image Video Action Generation Inference Framework☆2,756Updated this week
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆412Mar 2, 2026Updated 5 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,704Updated this week
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆430Jul 5, 2025Updated last year
- [NeurIPS 2025 Spotlight] LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation☆122Jun 22, 2026Updated 2 months ago
- TurboDiffusion: 100–200× Acceleration for Video Diffusion Models☆3,630Updated this week
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,692Jan 17, 2026Updated 7 months ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,938Mar 7, 2026Updated 5 months ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆709Jul 4, 2026Updated last month
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,042Feb 25, 2026Updated 6 months ago
- Distributed Compiler and Optimized Parallel Kernels☆1,530Aug 12, 2026Updated 2 weeks ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆2,181Updated this week
- Fast and Memory-Efficient Exact Attention (BF16/FP16/FP8/FP4) for Large Headdim, 1.5x~15x speedup over PyTorch SDPA.☆329Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,298Updated this week
- Making Flux go brrr on GPUs.☆172Jan 5, 2026Updated 7 months ago
- Unofficial extension implementation of Self-Forcing to support I2V && 14B training.☆386Sep 29, 2025Updated 11 months ago
- A curated list of research papers, resources, and advancements on Diffusion Cache and related efficient diffusion model acceleration tech…☆89Jul 23, 2026Updated last month
- rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale☆795Jun 25, 2026Updated 2 months ago
- Model Compression Toolbox for Large Language Models and Diffusion Models☆799Aug 14, 2025Updated last year
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆607Nov 11, 2025Updated 9 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆929Updated this week
- (NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis☆1,443Mar 5, 2025Updated last year
- Qwen-Image-Lightning: Speed up Qwen-Image model with distillation☆1,356Updated this week
- A framework for efficient model inference with omni-modality models☆6,507Updated this week
- High performance inference engine for diffusion models☆107Sep 5, 2025Updated 11 months ago
- [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆2,506May 7, 2026Updated 3 months ago
- Aiming to integrate most existing feature caching-based diffusion acceleration schemes into a unified framework.☆112Oct 23, 2025Updated 10 months ago
- ☆432Updated this week
- A forked version of flux-fast that makes flux-fast even faster with cache-dit, 3.3x speedup on NVIDIA L20.☆24Jul 18, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- A parallelism VAE avoids OOM for high resolution image generation☆95Aug 20, 2026Updated last week
- [ICLR 2026] Official implementation of DiCache: Let Diffusion Model Determine Its Own Cache☆64Jan 26, 2026Updated 7 months ago
- Official implementation of AsymFlow, pi-Flow, GMFlow☆464Jul 14, 2026Updated last month
- The official code for NeurIPS 2025 "MagCache: Fast Video Generation with Magnitude-Aware Cache"☆277Nov 17, 2025Updated 9 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,357Aug 28, 2025Updated last year
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,430Aug 7, 2025Updated last year
- Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.☆11,862Updated this week