xdit-project / DiTCacheAnalysisLinks
An auxiliary project analysis of the characteristics of KV in DiT Attention.
☆32Updated 10 months ago
Alternatives and similar repositories for DiTCacheAnalysis
Users that are interested in DiTCacheAnalysis are comparing it to the libraries listed below
Sorting:
- Quantized Attention on GPU☆44Updated 11 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆50Updated last year
- A parallelism VAE avoids OOM for high resolution image generation☆81Updated 2 months ago
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]☆43Updated last month
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆41Updated last month
- Patch convolution to avoid large GPU memory usage of Conv2D☆92Updated 9 months ago
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆60Updated 3 months ago
- 🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …☆87Updated last month
- ☆50Updated 5 months ago
- ☆39Updated 2 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆239Updated 3 months ago
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆113Updated this week
- ☆182Updated 9 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆78Updated last year
- Fast and memory-efficient exact kmeans☆113Updated this week
- ☆101Updated 5 months ago
- 16-fold memory access reduction with nearly no loss☆105Updated 7 months ago
- A sparse attention kernel supporting mix sparse patterns☆322Updated 8 months ago
- ☆31Updated 3 months ago
- ☆65Updated 6 months ago
- [ECCV24] MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization☆45Updated 11 months ago
- ☆120Updated 2 months ago
- [CVPR 2025] Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers☆67Updated last year
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆46Updated 3 months ago
- Debug print operator for cudagraph debugging☆14Updated last year
- Code for Draft Attention☆91Updated 5 months ago
- DeeperGEMM: crazy optimized version☆72Updated 5 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆126Updated 7 months ago
- High performance inference engine for diffusion models☆94Updated last month
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆18Updated 11 months ago