NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention

Large language model inference on Central Processing Units (CPU) is challenging due to the vast quantities of expensive Multiply-Add (MAD) matrix operations in the attention computations. In this paper, we argue that there is a rare gem in modern CPUs, Single-Instruction-Multiple-Data (SIMD) registers, which allow for ultra-low-latency lookups in batch. We leverage this unique capability of CPUs to propose NoMAD-Attention, an efficient attention algorithm that replaces MAD operations with in-register lookups. Through hardware-aware algorithmic designs, NoMAD-Attention achieves the computation of attention scores using repeated fast accesses to SIMD registers despite their highly limited sizes. Moreover, NoMAD-Attention works with pre-trained attention-based LLMs without model finetuning. Empirical evaluations demonstrate that NoMAD-Attention maintains the quality of the original LLMs well, and speeds up the 4-bit quantized LLaMA-7B-based model by up to 2$\times$ at 16k context length. Our results are reproducible at https://github.com/tonyzhang617/nomad-dist.

Wisdom of Committee: Distilling from Foundation Model to Specialized Application Model

Recent advancements in foundation models have yielded impressive performance across a wide range of tasks. Meanwhile, for specific applications, practitioners have been developing specialized application models. To enjoy the benefits of both kinds of models, one natural path is to transfer the knowledge in foundation models into specialized application models, which are generally more efficient for serving. Techniques from knowledge distillation may be applied here, where the application model learns to mimic the foundation model. However, specialized application models and foundation models have substantial gaps in capacity, employing distinct architectures, using different input features from different modalities, and being optimized on different distributions. These differences in model characteristics lead to significant challenges for distillation methods. In this work, we propose creating a teaching committee comprising both foundation model teachers and complementary teachers. Complementary teachers possess model characteristics akin to the student's, aiming to bridge the gap between the foundation model and specialized application models for a smoother knowledge transfer. Further, to accommodate the dissimilarity among the teachers in the committee, we introduce DiverseDistill, which allows the student to understand the expertise of each teacher and extract task knowledge. Our evaluations demonstrate that adding complementary teachers enhances student performance. Finally, DiverseDistill consistently outperforms baseline distillation methods, regardless of the teacher choices, resulting in significantly improved student performance.

Wisdom of Committee: Distilling from Foundation Model to SpecializedApplication Model

Recent advancements in foundation models have yielded impressive performance across a wide range of tasks. Meanwhile, for specific applications, practitioners have been developing specialized application models. To enjoy the benefits of both kinds of models, one natural path is to transfer the knowledge in foundation models into specialized application models, which are generally more efficient for serving. Techniques from knowledge distillation may be applied here, where the application model learns to mimic the foundation model. However, specialized application models and foundation models have substantial gaps in capacity, employing distinct architectures, using different input features from different modalities, and being optimized on different distributions. These differences in model characteristics lead to significant challenges for distillation methods. In this work, we propose creating a teaching committee comprising both foundation model teachers and complementary teachers. Complementary teachers possess model characteristics akin to the student's, aiming to bridge the gap between the foundation model and specialized application models for a smoother knowledge transfer. Further, to accommodate the dissimilarity among the teachers in the committee, we introduce DiverseDistill, which allows the student to understand the expertise of each teacher and extract task knowledge. Our evaluations demonstrate that adding complementary teachers enhances student performance. Finally, DiverseDistill consistently outperforms baseline distillation methods, regardless of the teacher choices, resulting in significantly improved student performance.

Learning Scalable Structural Representations for Link Prediction with Bloom Signatures

Graph neural networks (GNNs) have shown great potential in learning on graphs, but they are known to perform sub-optimally on link prediction tasks. Existing GNNs are primarily designed to learn node-wise representations and usually fail to capture pairwise relations between target nodes, which proves to be crucial for link prediction. Recent works resort to learning more expressive edge-wise representations by enhancing vanilla GNNs with structural features such as labeling tricks and link prediction heuristics, but they suffer from high computational overhead and limited scalability. To tackle this issue, we propose to learn structural link representations by augmenting the message-passing framework of GNNs with Bloom signatures. Bloom signatures are hashing-based compact encodings of node neighborhoods, which can be efficiently merged to recover various types of edge-wise structural features. We further show that any type of neighborhood overlap-based heuristic can be estimated by a neural network that takes Bloom signatures as input. GNNs with Bloom signatures are provably more expressive than vanilla GNNs and also more scalable than existing edge-wise models. Experimental results on five standard link prediction benchmarks show that our proposed model achieves comparable or better performance than existing edge-wise GNN models while being 3-200 $\times$ faster and more memory-efficient for online inference.

Contractive error feedback for gradient compression

On-device memory concerns in distributed deep learning have become severe due to (i) the growth of model size in multi-GPU training, and (ii) the wide adoption of deep neural networks for federated learning on IoT devices which have limited storage. In such settings, communication efficient optimization methods are attractive alternatives, however they still struggle with memory issues. To tackle these challenges, we propose an communication efficient method called contractive error feedback (ConEF). As opposed to SGD with error-feedback (EFSGD) that inefficiently manages memory, ConEF obtains the sweet spot of convergence and memory usage, and achieves communication efficiency by leveraging biased and all-reducable gradient compression. We empirically validate ConEF on various learning tasks that include image classification, language modeling, and machine translation and observe that ConEF saves 80\% - 90\% of the extra memory in EFSGD with almost no loss on test performance, while also achieving 1.3x - 5x speedup of SGD. Through our work, we also demonstrate the feasibility and convergence of ConEF to clear up the theoretical barrier of integrating ConEF to popular memory efficient frameworks such as ZeRO-3.

Adaptive Sampling for Deep Learning via Efficient Nonparametric Proxies

Data sampling is an effective method to improve the training speed of neural networks, with recent results demonstrating that it can even break the neural scaling laws. These results critically rely on high-quality scores to estimate the importance of an input to the network. We observe that there are two dominant strategies: static sampling, where the scores are determined before training, and dynamic sampling, where the scores can depend on the model weights. Static algorithms are computationally inexpensive but less effective than their dynamic counterparts, which can cause end-to-end slowdown due to their need to explicitly compute losses. To address this problem, we propose a novel sampling distribution based on nonparametric kernel regression that learns an effective importance score as the neural network trains. However, nonparametric regression models are too computationally expensive to accelerate end-to-end training. Therefore, we develop an efficient sketch-based approximation to the Nadaraya-Watson estimator. Using recent techniques from high-dimensional statistics and randomized algorithms, we prove that our Nadaraya-Watson sketch approximates the estimator with exponential convergence guarantees. Our sampling algorithm outperforms the baseline in terms of wall-clock time and accuracy on four datasets.

Heterogeneous federated collaborative filtering using FAIR: Federated Averaging in Random Subspaces

Recommendation systems (RS) for items (e.g., movies, books) and ads are widely used to tailor content to users on various internet platforms. Traditionally, recommendation models are trained on a central server. However, due to rising concerns for data privacy and regulations like the GDPR, federated learning is an increasingly popular paradigm in which data never leaves the client device. Applying federated learning to recommendation models is non-trivial due to large embedding tables, which often exceed the memory constraints of most user devices. To include data from all devices in federated learning, we must enable collective training of embedding tables on devices with heterogeneous memory capacities. Current solutions to heterogeneous federated learning can only accommodate a small range of capacities and thus limit the number of devices that can participate in training. We present Federated Averaging in Random subspaces (FAIR), which allows arbitrary compression of embedding tables based on device capacity and ensures the participation of all devices in training. FAIR uses what we call consistent and collapsible subspaces defined by hashing-based random projections to jointly train large embedding tables while using varying amounts of compression on user devices. We evaluate FAIR on Neural Collaborative Filtering tasks with multiple datasets and verify that FAIR can gather and share information from a wide range of devices with varying capacities, allowing for seamless collaboration. We prove the convergence of FAIR in the homogeneous setting with non-i.i.d data distribution. Our code is open source at {https://github.com/apd10/FLCF}

Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time

Large language models (LLMs) with hundreds of billions of parameters have sparked a new wave of exciting AI applications. However, they are computationally expensive at inference time. Sparsity is a natural approach to reduce this cost, but existing methods either require costly retraining, have to forgo LLM's in-context learning ability, or do not yield wall-clock time speedup on modern hardware. We hypothesize that contextual sparsity, which are small, input-dependent sets of attention heads and MLP parameters that yield approximately the same output as the dense model for a given input, can address these issues. We show that contextual sparsity exists, that it can be accurately predicted, and that we can exploit it to speed up LLM inference in wall-clock time without compromising LLM's quality or in-context learning ability. Based on these insights, we propose DejaVu, a system that uses a low-cost algorithm to predict contextual sparsity on the fly given inputs to each layer, along with an asynchronous and hardware-aware implementation that speeds up LLM inference. We validate that DejaVu can reduce the inference latency of OPT-175B by over 2X compared to the state-of-the-art FasterTransformer, and over 6X compared to the widely used Hugging Face implementation, without compromising model quality. The code is available at https://github.com/FMInference/DejaVu.

In defense of parameter sharing for model-compression

When considering a model architecture, there are several ways to reduce its memory footprint. Historically, popular approaches included selecting smaller architectures and creating sparse networks through pruning. More recently, randomized parameter-sharing (RPS) methods have gained traction for model compression at start of training. In this paper, we comprehensively assess the trade-off between memory and accuracy across RPS, pruning techniques, and building smaller models. Our findings demonstrate that RPS, which is both data and model-agnostic, consistently outperforms/matches smaller models and all moderately informed pruning strategies, such as MAG, SNIP, SYNFLOW, and GRASP, across the entire compression range. This advantage becomes particularly pronounced in higher compression scenarios. Notably, even when compared to highly informed pruning techniques like Lottery Ticket Rewinding (LTR), RPS exhibits superior performance in high compression settings. This points out inherent capacity advantage that RPS enjoys over sparse models. Theoretically, we establish RPS as a superior technique in terms of memory-efficient representation when compared to pruning for linear models. This paper argues in favor of paradigm shift towards RPS based models. During our rigorous evaluation of RPS, we identified issues in the state-of-the-art RPS technique ROAST, specifically regarding stability (ROAST's sensitivity to initialization hyperparameters, often leading to divergence) and Pareto-continuity (ROAST's inability to recover the accuracy of the original model at zero compression). We provably address both of these issues. We refer to the modified RPS, which incorporates our improvements, as STABLE-RPS.

Zen: Near-Optimal Sparse Tensor Synchronization for Distributed DNN Training

Distributed training is the de facto standard to scale up the training of Deep Neural Networks (DNNs) with multiple GPUs. The performance bottleneck of distributed training lies in communications for gradient synchronization. Recently, practitioners have observed sparsity in gradient tensors, suggesting the potential to reduce the traffic volume in communication and improve end-to-end training efficiency. Yet, the optimal communication scheme to fully leverage sparsity is still missing. This paper aims to address this gap. We first analyze the characteristics of sparse tensors in popular DNN models to understand the fundamentals of sparsity. We then systematically explore the design space of communication schemes for sparse tensors and find the optimal one. % We then find the optimal scheme based on the characteristics by systematically exploring the design space. We also develop a gradient synchronization system called Zen that approximately realizes it for sparse tensors. We demonstrate that Zen can achieve up to 5.09x speedup in communication time and up to 2.48x speedup in training throughput compared to the state-of-the-art methods.