xdit-project / DiTCacheAnalysis
An auxiliary project analysis of the characteristics of KV in DiT Attention.
☆28Updated 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 4 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆43Updated 8 months ago
- XAttention: Block Sparse Attention with Antidiagonal Scoring☆102Updated this week
- A parallelism VAE avoids OOM for high resolution image generation☆57Updated 2 months ago
- Patch convolution to avoid large GPU memory usage of Conv2D☆84Updated 2 months ago
- ☆153Updated 2 months ago
- A WebUI for Side-by-Side Comparison of Media (Images/Videos) Across Multiple Folders☆21Updated last month
- [CVPR 2025] Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers☆43Updated 6 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆62Updated this week
- ☆65Updated 2 months ago
- Triton implement of bi-directional (non-causal) linear attention☆44Updated last month
- DeeperGEMM: crazy optimized version☆61Updated last week
- 16-fold memory access reduction with nearly no loss☆81Updated this week
- Transformers components but in Triton☆32Updated this week
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆18Updated 4 months ago
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆40Updated 8 months ago
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆98Updated 8 months ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆39Updated last year
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆67Updated this week
- A sparse attention kernel supporting mix sparse patterns☆168Updated last month
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆59Updated 5 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆104Updated this week
- Odysseus: Playground of LLM Sequence Parallelism☆66Updated 9 months ago
- Debug print operator for cudagraph debugging☆10Updated 7 months ago
- Estimate MFU for DeepSeekV3☆19Updated 2 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆34Updated 7 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆35Updated 9 months ago
- Implementation for the paper: CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference☆16Updated 2 weeks ago
- SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆17Updated 5 months ago
- Efficient Mixture of Experts for LLM Paper List☆45Updated 3 months ago