408 citations · 789 across the 11 of their papers we have counts for
12 papers
FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models
Bowen Xue, Zihan Min, Xingyang Li +8
Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications. Howeve…
DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
Junyu Chen, Wenkun He, Yuchao Gu +12
We introduce DC-VideoGen, a post-training acceleration framework for efficient video generation. DC-VideoGen can be applied to any pre-trained video diffusion model, improving effi…
LEGO: Spatial Accelerator Generation and Optimization for Tensor Applications
Yujun Lin, Zhekai Zhang, Song Han
Modern tensor applications, especially foundation models and generative AI applications require multiple input modalities (both vision and language), which increases the demand for…
DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
Wenkun He, Yuchao Gu, Junyu Chen +11
Existing text-to-image diffusion models excel at generating high-quality images, but face significant efficiency challenges when scaled to high resolutions, like 4K image generatio…
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
Enze Xie, Junsong Chen, Yuyang Zhao +11
This paper presents SANA-1.5, a linear Diffusion Transformer for efficient scaling in text-to-image generation. Building upon SANA-1.0, we introduce three key innovations: (1) Effi…
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
Muyang Li, Yujun Lin, Zhekai Zhang +7
Diffusion models can effectively generate high-quality images. However, as they scale, rising memory demands and higher latency pose substantial deployment challenges. In this work…
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
Enze Xie, Junsong Chen, Junyu Chen +8
We introduce Sana, a text-to-image framework that can efficiently generate images up to 40964096 resolution. Sana can synthesize high-resolution, high-quality images with s…
QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving
Yujun Lin, Haotian Tang, Shang Yang +4
Quantization can accelerate large language model (LLM) inference. Going beyond INT8 quantization, the research community is actively exploring even lower precision, such as INT4. N…
Lightening-Transformer: A Dynamically-operated Optically-interconnected Photonic Transformer Accelerator
Hanqing Zhu, Jiaqi Gu, Hanrui Wang +7
The wide adoption and significant computing resource of attention-based transformers, e.g., Vision Transformers and large language models (LLM), have driven the demand for efficien…
PointAcc: Efficient Point Cloud Accelerator
Yujun Lin, Zhekai Zhang, Haotian Tang +2
Deep learning on point clouds plays a vital role in a wide range of applications such as autonomous driving and AR/VR. These applications interact with people in real-time on edge…
SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
Hanrui Wang, Zhekai Zhang, Song Han
The attention mechanism is becoming increasingly popular in Natural Language Processing (NLP) applications, showing superior performance than convolutional and recurrent architectu…
SpArch: Efficient Architecture for Sparse Matrix Multiplication
Zhekai Zhang, Hanrui Wang, Song Han +1
Generalized Sparse Matrix-Matrix Multiplication (SpGEMM) is a ubiquitous task in various engineering and scientific applications. However, inner product based SpGENN introduces red…