KsanaDiT: High-Performance DiT (Diffusion Transformer) Inference Framework for Video & Image Generation
☆54May 13, 2026Updated 3 weeks ago
Alternatives and similar repositories for KsanaDiT
Users that are interested in KsanaDiT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An out-of-the-box inference acceleration engine for Diffusion and DiT models☆60Mar 21, 2025Updated last year
- ☆143Aug 18, 2025Updated 9 months ago
- [WIP] Better (FP8) attention for Hopper☆34Feb 24, 2025Updated last year
- CPU Memory Compiler and Parallel programing☆26Nov 18, 2024Updated last year
- 重构nerf 代码，更加容易读懂☆13Mar 26, 2023Updated 3 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆58Oct 15, 2025Updated 7 months ago
- ☆31May 27, 2021Updated 5 years ago
- Multi-Level Triton Runner supporting Python, IR, PTX, AMDGCN, cubin and hasco.☆98May 8, 2026Updated last month
- Code for our paper 'Transform your Smartphone into a DSLR Camera: Learning the ISP in the Wild' accepted at ECCV 2022☆35Mar 30, 2023Updated 3 years ago
- ☆23Aug 20, 2025Updated 9 months ago
- Accepted to MLSys 2026☆85Apr 19, 2026Updated last month
- Combining Teacache with xDiT to Accelerate Visual Generation Models☆32Apr 21, 2025Updated last year
- UltraVSR: Achieving Ultra-Realistic Video Super-Resolution with Efficient One-Step Diffusion Space☆47Oct 17, 2025Updated 7 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 10 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆52May 1, 2026Updated last month
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆427Jul 5, 2025Updated 11 months ago
- AI for Frappe ERPNext☆44Updated this week
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆298Dec 1, 2025Updated 6 months ago
- ☆16Sep 12, 2023Updated 2 years ago
- Inference with YOLOv5, OpenCV 4.5.4 DNN, C++, ROS and Python☆13Feb 12, 2023Updated 3 years ago
- differentiable SLIC PyTorch☆23Sep 19, 2023Updated 2 years ago
- Tutorial Exercises and Code for GPU Communications Tutorial at HOT Interconnects 2025☆32Oct 22, 2025Updated 7 months ago
- High Performance FP8 GEMM Kernels for SM89 and later GPUs.☆21Jan 24, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- A PyTorch implementation of computing mean average precision in parallel☆16Jul 7, 2022Updated 3 years ago
- This is the official repo for the paper "Accelerating Parallel Sampling of Diffusion Models" Tang et al. ICML 2024 https://openreview.net…☆16Jul 19, 2024Updated last year
- A parallelism VAE avoids OOM for high resolution image generation☆94May 8, 2026Updated last month
- A Triton JIT runtime and ffi provider in C++☆35May 27, 2026Updated last week
- In our implementation of Qwen-Image-Edit, we employ block causal attention to improve inference speed.☆51Feb 16, 2026Updated 3 months ago
- ☆20Jan 1, 2026Updated 5 months ago
- Open source simulator for porous media flow☆14Oct 15, 2022Updated 3 years ago
- Flash-Linear-Attention models beyond language☆21Aug 28, 2025Updated 9 months ago
- ☆52Nov 3, 2025Updated 7 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆14May 25, 2023Updated 3 years ago
- ☆18Feb 28, 2023Updated 3 years ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆672May 21, 2026Updated 2 weeks ago
- ☆12Oct 9, 2025Updated 7 months ago
- CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs☆193May 22, 2026Updated 2 weeks ago
- torch_quantizer is a out-of-box quantization tool for PyTorch models on CUDA backend, specially optimized for Diffusion Models.☆25Mar 29, 2024Updated 2 years ago
- PyTorch implementation of "Towards Interpretable Video Super-Resolution via Alternating Optimization (ECCV2022)"☆74Mar 28, 2024Updated 2 years ago