xdit-project / DiTCacheAnalysis
An auxiliary project analysis of the characteristics of KV in DiT Attention.
☆27Updated 3 months ago
Alternatives and similar repositories for DiTCacheAnalysis:
Users that are interested in DiTCacheAnalysis are comparing it to the libraries listed below
- Quantized Attention on GPU☆45Updated 3 months ago
- A parallelism VAE avoids OOM for high resolution image generation☆56Updated last month
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆42Updated 7 months ago
- ☆149Updated 2 months ago
- Patch convolution to avoid large GPU memory usage of Conv2D☆85Updated last month
- A WebUI for Side-by-Side Comparison of Media (Images/Videos) Across Multiple Folders☆21Updated 3 weeks ago
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆38Updated 8 months ago
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆18Updated 3 months ago
- Triton implement of bi-directional (non-causal) linear attention☆43Updated last month
- 16-fold memory access reduction with nearly no loss☆80Updated 3 weeks ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆59Updated 2 weeks ago
- [CVPR 2025] Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers☆38Updated 6 months ago
- [ECCV24] MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization☆33Updated 3 months ago
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆94Updated 7 months ago
- A sparse attention kernel supporting mix sparse patterns☆159Updated last month
- ☆62Updated last month
- Odysseus: Playground of LLM Sequence Parallelism☆66Updated 8 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆103Updated this week
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆59Updated last week
- A light-weight and high-efficient training framework for accelerating diffusion tasks.☆46Updated 6 months ago
- Transformers components but in Triton☆32Updated 3 months ago
- IntLLaMA: A fast and light quantization solution for LLaMA☆18Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆70Updated 4 months ago
- Debug print operator for cudagraph debugging☆10Updated 7 months ago
- ☆42Updated last month
- Vocabulary Parallelism☆17Updated this week
- This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality"☆46Updated last month
- SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆16Updated 5 months ago