πA curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.π
β532Mar 19, 2026Updated 3 weeks ago
Alternatives and similar repositories for Awesome-DiT-Inference
Users that are interested in Awesome-DiT-Inference are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- πA curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.πβ5,130Updated this week
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic cachingβ427Jul 5, 2025Updated 9 months ago
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelismβ2,586Apr 1, 2026Updated last week
- A PyTorch-native inference engine with hybrid cache acceleration and massive parallelism for DiTs.β1,120Apr 3, 2026Updated last week
- (WIP) Parallel inference for black-forest-labs' FLUX model.β19Nov 18, 2024Updated last year
- Proton VPN Special Offer - Get 70% off β’ AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- π Collection of awesome generation acceleration resources.β398Jul 7, 2025Updated 9 months ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeersβ383Mar 2, 2026Updated last month
- πLeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginnersπ, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.πβ10,217Updated this week
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Modelsβ726Dec 2, 2024Updated last year
- Quantized Attention on GPUβ44Nov 22, 2024Updated last year
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Cachingβ215Mar 14, 2025Updated last year
- Distributed Compiler based on Triton for Parallel Systemsβ1,401Mar 11, 2026Updated 3 weeks ago
- β191Jan 14, 2025Updated last year
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Modelβ1,301Jun 8, 2025Updated 10 months ago
- Managed Database hosting by DigitalOcean β’ AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- π€FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3xβπ vs SDPA EA.β257Feb 13, 2026Updated last month
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"β171Nov 5, 2024Updated last year
- A curated list of research papers, resources, and advancements on Diffusion Cache and related efficient diffusion model acceleration techβ¦β79Nov 4, 2025Updated 5 months ago
- A parallelism VAE avoids OOM for high resolution image generationβ89Mar 12, 2026Updated 3 weeks ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationβ157Mar 21, 2025Updated last year
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.β55Jul 8, 2024Updated last year
- FlashInfer: Kernel Library for LLM Servingβ5,273Updated this week
- β‘οΈWrite HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peakβ‘οΈ Performance.β150May 10, 2025Updated 11 months ago
- A unified inference and post-training framework for accelerated video generation.β3,341Apr 3, 2026Updated last week
- Managed hosting for WordPress and PHP on Cloudways β’ AdManaged hosting with the flexibility to host WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Cloudways by DigitalOcean.
- Aiming to integrate most existing feature caching-based diffusion acceleration schemes into a unified framework.β98Oct 23, 2025Updated 5 months ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-tβ¦β3,280Jan 17, 2026Updated 2 months ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of papβ¦β282Mar 6, 2025Updated last year
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Trainingβ765Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernelsβ5,460Apr 3, 2026Updated last week
- β52May 19, 2025Updated 10 months ago
- [CVPR 2024] DeepCache: Accelerating Diffusion Models for Freeβ964Jun 27, 2024Updated last year
- A throughput-oriented high-performance serving framework for LLMsβ953Mar 29, 2026Updated last week
- β109Mar 12, 2026Updated 3 weeks ago
- Wordpress hosting with auto-scaling on Cloudways β’ AdFully Managed hosting built for WordPress-powered businesses that need reliable, auto-scalable hosting. Cloudways SafeUpdates now available.
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inferenceβ660Jan 15, 2026Updated 2 months ago
- A sparse attention kernel supporting mix sparse patternsβ495Jan 18, 2026Updated 2 months ago
- VideoSys: An easy and efficient system for video generationβ2,021Aug 27, 2025Updated 7 months ago
- how to optimize some algorithm in cuda.β2,910Apr 1, 2026Updated last week
- A low-latency & high-throughput serving engine for LLMsβ490Jan 8, 2026Updated 3 months ago
- High performance inference engine for diffusion modelsβ107Sep 5, 2025Updated 7 months ago
- β12Jul 24, 2024Updated last year