🤗 A PyTorch-native and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.
☆1,058Updated this week
Alternatives and similar repositories for cache-dit
Users that are interested in cache-dit are comparing it to the libraries listed below
Sorting:
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,549Updated this week
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆525Updated this week
- A unified inference and post-training framework for accelerated video generation.☆3,111Updated this week
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆424Jul 5, 2025Updated 7 months ago
- [ICLR 2026] Official implementation of DiCache: Let Diffusion Model Determine Its Own Cache☆55Jan 26, 2026Updated last month
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆251Feb 13, 2026Updated 2 weeks ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆373Feb 16, 2026Updated 2 weeks ago
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,271Jun 8, 2025Updated 8 months ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆629Feb 3, 2026Updated 3 weeks ago
- Qwen-Image-Lightning: Speed up Qwen-Image model with distillation☆1,244Jan 1, 2026Updated 2 months ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,703Feb 14, 2026Updated 2 weeks ago
- Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference☆1,256Updated this week
- FlashInfer: Kernel Library for LLM Serving☆5,009Feb 23, 2026Updated last week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆759Aug 14, 2025Updated 6 months ago
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆952Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,361Feb 13, 2026Updated 2 weeks ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆644Jan 15, 2026Updated last month
- Light Image Video Generation Inference Framework☆1,970Feb 11, 2026Updated 2 weeks ago
- Implementation of SmoothCache, a project aimed at speeding-up Diffusion Transformer (DiT) based GenAI models with error-guided caching.☆47Jul 17, 2025Updated 7 months ago
- ☆190Jan 14, 2025Updated last year
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,182Jan 17, 2026Updated last month
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆149Mar 21, 2025Updated 11 months ago
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆1,676Updated this week
- Glance: Accelerating Diffusion Models with 1 Sample☆152Dec 24, 2025Updated 2 months ago
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]☆46Feb 17, 2026Updated last week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,261Aug 28, 2025Updated 6 months ago
- lite attention implemented over flash attention 3☆45Updated this week
- A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresse…☆2,031Updated this week
- A parallelism VAE avoids OOM for high resolution image generation☆85Aug 4, 2025Updated 6 months ago
- High performance inference engine for diffusion models☆105Sep 5, 2025Updated 5 months ago
- OneDiff: An out-of-the-box acceleration library for diffusion models.☆1,970Dec 4, 2025Updated 2 months ago
- 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉☆9,755Updated this week
- https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.☆1,301Mar 27, 2025Updated 11 months ago
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,022Updated this week
- VideoSys: An easy and efficient system for video generation☆2,016Aug 27, 2025Updated 6 months ago
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,232Aug 7, 2025Updated 6 months ago
- A forked version of flux-fast that makes flux-fast even faster with cache-dit, 3.3x speedup on NVIDIA L20.☆24Jul 18, 2025Updated 7 months ago
- The official code for NeurIPS 2025 "MagCache: Fast Video Generation with Magnitude-Aware Cache"☆260Nov 17, 2025Updated 3 months ago
- MAGI-1: Autoregressive Video Generation at Scale☆3,643Jun 17, 2025Updated 8 months ago