14 accepted papers
Fine-tuning is a critical step for adapting large language models (LLMs) to domain-specific downstream tasks. To mitigate the substantial computational and memory costs of full-model fine-tuning, Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed to update only a small subset of model…
Sparse Mixture-of-Experts (MoE) allows scaling of language and vision models efficiently by activating only a small subset of experts per input. While this reduces computation, the large number of parameters still incurs substantial memory overhead during inference. Post-training quantization has be…
Rotary Positional Embedding (RoPE) is a widely adopted technique for encoding position in language models, which, while effective, causes performance breakdown when input length exceeds training length. Prior analyses assert (rightly) that long inputs cause channels to rotate "out of distribution,"…
Hybrid Mamba-Transformer models have emerged as promising alternatives to pure Transformers, offering efficiency and competitive performance. However, they struggle to generalize beyond their training context windows, collapsing on long-context tasks. We provide the first systematic analysis of this…
Microscaling data formats leverage per-block tensor quantization to enable aggressive model compression with limited loss in accuracy. Unlocking their potential for efficient training and inference necessitates hardware-friendly implementations that handle matrix multiplications in a native format a…
The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks (experts), through trainable routers. MoE reduces the training computation significantly for large models, but its deployment can be still memory/computation expensive for some downstream tasks.…
In this paper, we present a simple optimization-based preprocessing technique called Weight Magnitude Reduction (MagR) to improve the performance of post-training quantization. For each linear layer, we adjust the pre-trained floating-point weights by solving an $\ell_\infty$-regularized optimizatio…
Pre-trained transformer models have achieved remarkable success in natural language processing (NLP) and have recently become competitive alternatives to Convolution Neural Networks (CNN) and Recurrent Neural Networks (RNN) in vision and speech tasks, respectively. Due to excellent computational eff…
There is no doubt that making AI mainstream by bringing powerful, yet power hungry deep neural networks (DNNs) to resource-constrained devices would required an efficient co-design of algorithms, hardware and software. The increased popularity of DNN applications deployed on a wide variety of platfo…
Large-scale distributed training of Deep Neural Networks (DNNs) on state-of-the-art platforms are expected to be severely communication constrained. To overcome this limitation, numerous gradient compression techniques have been proposed and have demonstrated high compression ratios. However, most e…
In this paper, we propose a number of novel techniques and numerical representation formats that enable, for the very first time, the precision of training systems to be aggressively scaled from 8-bits to 4-bits. To enable this advance, we explore a novel adaptive Gradient Scaling technique (Gradsca…
Efforts to reduce the numerical precision of computations in deep learning training have yielded systems that aggressively quantize weights and activations, yet employ wide high-precision accumulators for partial sums in inner-product operations to preserve the quality of convergence. The absence of…
Reducing the numerical precision of data and computation is extremely effective in accelerating deep learning training workloads. Towards this end, 8-bit floating point representations (FP8) were recently proposed for DNN training. However, its applicability was demonstrated on a few selected models…
The state-of-the-art hardware platforms for training deep neural networks are moving from traditional single precision (32-bit) computations towards 16 bits of precision - in large part due to the high energy efficiency and smaller bit storage associated with using reduced-precision representations.…