An auxiliary project analysis of the characteristics of KV in DiT Attention.
☆33Nov 29, 2024Updated last year
Alternatives and similar repositories for DiTCacheAnalysis
Users that are interested in DiTCacheAnalysis are comparing it to the libraries listed below
Sorting:
- A parallelism VAE avoids OOM for high resolution image generation☆85Aug 4, 2025Updated 6 months ago
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- ☆190Jan 14, 2025Updated last year
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆19Nov 18, 2024Updated last year
- FlexAttention w/ FlashAttention3 Support☆27Oct 5, 2024Updated last year
- ☆32Jul 2, 2025Updated 8 months ago
- Manages vllm-nccl dependency☆17Jun 3, 2024Updated last year
- [VLDB 26, NeurIPS 25] Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆124Feb 22, 2026Updated last week
- Prefix-Aware Attention for LLM Decoding☆29Jan 23, 2026Updated last month
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆71Nov 4, 2024Updated last year
- [ICDCS 2023] Evaluation and Optimization of Gradient Compression for Distributed Deep Learning☆10Apr 28, 2023Updated 2 years ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆144Dec 4, 2024Updated last year
- A sparse attention kernel supporting mix sparse patterns☆467Jan 18, 2026Updated last month
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆91Feb 23, 2026Updated last week
- diffusers with search engine☆11Jan 13, 2026Updated last month
- DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing (WACV 2025)☆12Feb 7, 2026Updated 3 weeks ago
- ☆11Apr 3, 2023Updated 2 years ago
- FPGA-based HyperLogLog Accelerator☆12Jul 13, 2020Updated 5 years ago
- PSTensor provides a way to hack the memory management of tensors in TensorFlow and PyTorch by defining your own C++ Tensor Class.☆10Feb 10, 2022Updated 4 years ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆24Nov 21, 2024Updated last year
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆259Dec 27, 2024Updated last year
- 🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …☆101Sep 8, 2025Updated 5 months ago
- Estimate MFU for DeepSeekV3☆26Jan 5, 2025Updated last year
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆117Jul 15, 2024Updated last year
- Artifact evaluation repo for EuroSys'24.☆29Nov 7, 2023Updated 2 years ago
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆93Dec 2, 2025Updated 3 months ago
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆724Dec 2, 2024Updated last year
- ☆33Jan 6, 2025Updated last year
- ☆13Nov 29, 2024Updated last year
- ☆19Jun 1, 2025Updated 9 months ago
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆167Nov 5, 2024Updated last year
- Implementation from scratch in C of the Multi-head latent attention used in the Deepseek-v3 technical paper.☆18Jan 15, 2025Updated last year
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆60Mar 25, 2025Updated 11 months ago
- Patch convolution to avoid large GPU memory usage of Conv2D☆95Jan 23, 2025Updated last year
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆57Jul 23, 2024Updated last year
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆262Nov 18, 2024Updated last year
- Framework to reduce autotune overhead to zero for well known deployments.☆97Sep 19, 2025Updated 5 months ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆250Dec 16, 2024Updated last year
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆41May 13, 2025Updated 9 months ago