Mixed-precision networks allow for a variable bit-width quantization for every layer in the network. A major limitation of existing work is that the bit-width for each layer must be predefined during training time. This allows little flexibility if the characteristics of the device on which the network is deployed change during runtime. In this work, we propose Bit-Mixer, the very first method to train a meta-quantized network where during test time any layer can change its bid-width without affecting at all the overall network's ability for highly accurate inference. To this end, we make 2 key contributions: (a) Transitional Batch-Norms, and (b) a 3-stage optimization process which is shown capable of training such a network. We show that our method can result in mixed precision networks that exhibit the desirable flexibility properties for on-device deployment without compromising accuracy. Code will be made available.
MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM
University of Arizona（亚利桑那大学）；Duke University（杜克大学）；Sungkyunkwan University（成均馆大学）；Panasonic AI Lab（松下人工智能实验室）；Korea Advanced Institute of Science and Technology（韩国科学技术院）
TRINE: A Token-Aware, Runtime-Adaptive FPGA Inference Engine for Multimodal AI
University of California, Irvine（加州大学尔湾分校）；Purdue University Northwest（北达科他州立大学）；Qualcomm（高通）；Samsung（三星）
针对多模态AI中不同计算/内存模式导致嵌入式平台实时性不足的问题，提出TRINE，一种无需重配置的单比特流FPGA加速器与编译器，通过统一层映射、运行时模式切换、令牌剪枝和依赖感知层卸载，实现端到端多模态推理，在Alveo U50和ZCU104上相比RTX 4090和Jetson Orin Nano分别降低延迟22.57倍和6.86倍，功耗仅20-21W。
TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision
Department of Electrical and Computer Engineering（电气与计算机工程系）；School of Electronic and Electrical Engineering（电子与电气工程学院）；Department of Artificial Intelligence（人工智能系）
Loom: Exploiting Weight and Activation Precisions to Accelerate Convolutional Neural Networks
University of Toronto（多伦多大学）
介绍了一种用于卷积神经网络（CNN）的硬件推理加速器Loom（LM）。在LM中，可以节省的每一位数据精度都转化为成比例的性能增益。具体来说，对于卷积层，LM的执行时间与权重和激活的精度成反比。对于全连接层，LM的性能与权重的精度成反比。LM的目标是面积和带宽受限的片上系统设计，例如那些在移动设备上无法负担存储片上每层所需的多兆字节缓冲区的设计。因此，在给定数据带宽预算的情况下，LM相对于等效的位并行加速器提高了能量效率和性能。对于权重和激活，LM可以利用轮廓导出的每层精度。然而，在运行时，LM进一步以比层粒度小得多的粒度调整激活精度。此外，它可以自然地以比层更小的粒度利用权重精度可变性。平均而言，在几个图像分类CNN中，对于每个周期可以执行相当于128个16 b x 16 b乘法累加操作的配置，LM的性能比最先进的位并行加速器[1]高出4.38倍，而精度没有任何损失，同时能效高出3.54倍。LM可以在执行性能和能源效率的额外改进上权衡准确性，并且与仅针对激活精度的加速器相比是有利的。我们还研究了2位和4位LM变体，发现每周期2位变体是最节能的。
