xuyang-liu16 / Awesome-Generation-AccelerationLinks
π Collection of awesome generation acceleration resources.
β270Updated 2 months ago
Alternatives and similar repositories for Awesome-Generation-Acceleration
Users that are interested in Awesome-Generation-Acceleration are comparing it to the libraries listed below
Sorting:
- Accelerating Diffusion Transformers with Token-wise Feature Cachingβ159Updated 3 months ago
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsityβ344Updated 2 weeks ago
- β167Updated 5 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationβ102Updated 3 months ago
- Adaptive Caching for Faster Video Generation with Diffusion Transformersβ150Updated 7 months ago
- β310Updated 2 weeks ago
- This is a repo to track the latest autoregressive visual generation papers.β356Updated this week
- From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeersβ179Updated last month
- [CVPR 2025] π₯ Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".β337Updated 3 months ago
- (ToCa-v2) A New version of ToCaοΌwith faster speed and better acceleration!β37Updated 3 months ago
- πA curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Caching, Quantization, Parallelism, etc.β283Updated this week
- Scaling Diffusion Transformers with Mixture of Expertsβ339Updated 9 months ago
- [TMLR 2025π₯] A survey for the autoregressive models in vision.β638Updated this week
- [ICLR 2025] Autoregressive Video Generation without Vector Quantizationβ535Updated last month
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Cachingβ105Updated 11 months ago
- [CVPR 2024 Highlight & TPAMI 2025] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization forβ¦β65Updated last week
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional varβ¦β130Updated 4 months ago
- Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoningβ170Updated 3 weeks ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"β233Updated 2 weeks ago
- [ICLR 2025] OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generationβ304Updated 3 weeks ago
- SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Trainingβ180Updated 5 months ago
- A sparse attention kernel supporting mix sparse patternsβ238Updated 4 months ago
- [ICML 2025] This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Localityβ¦β49Updated 3 months ago
- The collection of awesome papers on alignment of diffusion models.β253Updated last week
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.β46Updated 11 months ago
- Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"β371Updated this week
- High-performance Image Tokenizers for VAR and ARβ273Updated 2 months ago
- β78Updated 3 months ago
- Curated list of methods that focuses on improving the efficiency of diffusion modelsβ45Updated 11 months ago
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cacheβ¦β113Updated last week