xlite-dev / Awesome-DiT-InferenceLinks
πA curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.π
β478Updated last month
Alternatives and similar repositories for Awesome-DiT-Inference
Users that are interested in Awesome-DiT-Inference are comparing it to the libraries listed below
Sorting:
- π€A PyTorch-native Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs: Z-Image, FLUX2, Qwen-Image, etc.β804Updated this week
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.β852Updated last week
- A sparse attention kernel supporting mix sparse patternsβ408Updated last week
- Model Compression Toolbox for Large Language Models and Diffusion Modelsβ722Updated 4 months ago
- High performance inference engine for diffusion modelsβ101Updated 3 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationβ142Updated 9 months ago
- β186Updated 11 months ago
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Modelsβ715Updated last year
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Trainingβ590Updated last week
- π Collection of awesome generation acceleration resources.β372Updated 5 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inferenceβ618Updated this week
- Puzzles for learning Triton, play it with minimal environment configuration!β576Updated 3 weeks ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attentionβ605Updated 2 weeks ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic cachingβ407Updated 5 months ago
- A parallelism VAE avoids OOM for high resolution image generationβ84Updated 4 months ago
- Aiming to integrate most existing feature caching-based diffusion acceleration schemes into a unified framework.β82Updated 2 months ago
- flash attention tutorial written in python, triton, cuda, cutlassβ462Updated 7 months ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeersβ347Updated 4 months ago
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable SparseβLinear Attentionβ199Updated this week
- β440Updated 4 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoringβ261Updated 5 months ago
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Cachingβ197Updated 9 months ago
- [ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.β368Updated last year
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.β577Updated this week
- π€FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3xβπ vs SDPA EA.β242Updated last month
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inferenceβ360Updated 5 months ago
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generationβ567Updated last month
- [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLM, VLM, and video generation models.β643Updated last month
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"β202Updated last month
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"β748Updated 3 weeks ago