Shan Huang

Jinhao Li, Jiaming Xu, Shiyao Li et al.

Large language models (LLMs) have demonstrated impressive abilities in various domains while the inference cost is expensive. Many previous studies exploit quantization methods to reduce LLM inference cost by reducing latency and memory consumption. Applying 2-bit single-precision weight quantization brings >3% accuracy loss, so the state-of-the-art methods use mixed-precision methods for LLMs (e.g. Llama2-7b, etc.) to improve the accuracy. However, challenges still exist: (1) Uneven distribution in weight matrix. (2) Large speed degradation by adding sparse outliers. (3) Time-consuming dequantization operations on GPUs. To tackle these challenges and enable fast and efficient LLM inference on GPUs, we propose the following techniques in this paper. (1) Intra-weight mixed-precision quantization. (2) Exclusive 2-bit sparse outlier with minimum speed degradation. (3) Asynchronous dequantization. We conduct extensive experiments on different model families (e.g. Llama3, etc.) and model sizes. We achieve 2.91-bit for each weight considering all scales/zeros for different models with negligible loss. As a result, with our 2/4/16 mixed-precision quantization for each weight matrix and asynchronous dequantization during inference, our design achieves an end-to-end speedup for Llama2-7b is 1.74x over the original model, and we reduce both runtime cost and total cost by up to 2.53x and 2.29x with less GPU requirements.

Bin Huang, Feihong Xu, Xinchong Shi et al.

In clinical practice, single-radiotracer positron emission tomography (PET) is commonly used for imaging. Although multi-tracer PET imaging can provide supplementary information of radiotracers that are sensitive to physiological function changes, enabling a more comprehensive characterization of physiological and pathological states, the gamma-photon pairs generated by positron annihilation reactions of different tracers in PET imaging have the same energy, making it difficult to distinguish the tracer signals. In this study, a multi-latent space guided texture conditional diffusion transformer model (MS-CDT) is proposed for PET tracer separation. To the best of our knowledge, this is the first attempt to use texture condition and multi-latent space for tracer separation in PET imaging. The proposed model integrates diffusion and transformer architectures into a unified optimization framework, with the novel addition of texture masks as conditional inputs to enhance image details. By leveraging multi-latent space prior derived from different tracers, the model captures multi-level feature representations, aiming to balance computational efficiency and detail preservation. The texture masks, serving as conditional guidance, help the model focus on salient structural patterns, thereby improving the extraction and utilization of fine-grained image textures. When combined with the diffusion transformer backbone, this conditioning mechanism contributes to more accurate and robust tracer separation. To evaluate its effectiveness, the proposed MS-CDT is compared with several advanced methods on two types of 3D PET datasets: brain and chest scans. Experimental results indicate that MS-CDT achieved competitive performance in terms of image quality and preservation of clinically relevant information. Code is available at: https://github.com/yqx7150/MS-CDT.