Diffusion models have achieved great success in image synthesis through iterative noise
estimation using deep neural networks. However, the slow inference, high memory …

Post-training quantization~(PTQ) of transformer language models faces significant
challenges due to the existence of detrimental outliers in activations. We observe that these …

Transformer-based large language models (LLMs) have achieved great success with the
growing model size. LLMs' size grows by 240× every two years, which outpaces the …

Learning to synthesize data has emerged as a promising direction in zero-shot quantization
(ZSQ), which represents neural networks by low-bit integer without accessing any of the real …

The complicated architecture and high training cost of vision transformers urge the
exploration of post-training quantization. However, the heavy-tailed distribution of vision …

Zero-shot quantization (ZSQ) is promising for compressing and accelerating deep neural
networks when the data for training full-precision models are inaccessible. In ZSQ, network …

Generative data-free quantization emerges as a practical compression approach that
quantizes deep neural networks to low bit-width without accessing the real data. This …

The DNN inferences are often batched for better utilizing the hardware in existing DNN
serving systems. However, DNN serving exhibits diversity in many aspects, such as input …

The rapid development of large language models (LLMs) has significantly transformed the
field of artificial intelligence, demonstrating remarkable capabilities in natural language …

We introduce Sana, a text-to-image framework that can efficiently generate images up to
4096$\times $4096 resolution. Sana can synthesize high-resolution, high-quality images …