Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Each LLM serving request goes through two phases. The first is prefill which processes the entire input prompt to produce one output token and the second is decode which generates the rest of output tokens, one-at-a-time. Prefill iterations have high latency but saturate GPU compute due to parallel processing of the input prompt. In contrast, decode iterations have low latency but also low compute utilization because a decode iteration processes only a single token per request. This makes batching highly effective for decodes and consequently for overall throughput. However, batching multiple requests leads to an interleaving of prefill and decode iterations which makes it challenging to achieve both high throughput and low latency. We introduce an efficient LLM inference scheduler Sarathi-Serve inspired by the techniques we originally proposed for optimizing throughput in Sarathi. Sarathi-Serve leverages chunked-prefills from Sarathi to create stall-free schedules that can add new requests in a batch without pausing ongoing decodes. Stall-free scheduling unlocks the opportunity to improve throughput with large batch sizes while minimizing the effect of batching on latency. Our evaluation shows that Sarathi-Serve improves serving throughput within desired latency SLOs of Mistral-7B by up to 2.6x on a single A100 GPU and up to 6.9x for Falcon-180B on 8 A100 GPUs over Orca and vLLM.

SuperServe: Fine-Grained Inference Serving for Unpredictable Workloads

The increasing deployment of ML models on the critical path of production applications in both datacenter and the edge requires ML inference serving systems to serve these models under unpredictable and bursty request arrival rates. Serving models under such conditions requires these systems to strike a careful balance between the latency and accuracy requirements of the application and the overall efficiency of utilization of scarce resources. State-of-the-art systems resolve this tension by either choosing a static point in the latency-accuracy tradeoff space to serve all requests or load specific models on the critical path of request serving. In this work, we instead resolve this tension by simultaneously serving the entire-range of models spanning the latency-accuracy tradeoff space. Our novel mechanism, SubNetAct, achieves this by carefully inserting specialized operators in weight-shared SuperNetworks. These operators enable SubNetAct to dynamically route requests through the network to meet a latency and accuracy target. SubNetAct requires upto 2.6x lower memory to serve a vastly-higher number of models than prior state-of-the-art. In addition, SubNetAct's near-instantaneous actuation of models unlocks the design space of fine-grained, reactive scheduling policies. We explore the design of one such extremely effective policy, SlackFit and instantiate both SubNetAct and SlackFit in a real system, SuperServe. SuperServe achieves 4.67% higher accuracy for the same SLO attainment and 2.85x higher SLO attainment for the same accuracy on a trace derived from the real-world Microsoft Azure Functions workload and yields the best trade-offs on a wide range of extremely-bursty synthetic traces automatically.

Signed Binarization: Unlocking Efficiency Through Repetition-Sparsity Trade-Off

Efficient inference of Deep Neural Networks (DNNs) on resource-constrained edge devices is essential. Quantization and sparsity are key algorithmic techniques that translate to repetition and sparsity within tensors at the hardware-software interface. This paper introduces the concept of repetition-sparsity trade-off that helps explain computational efficiency during inference. We propose Signed Binarization, a unified co-design framework that synergistically integrates hardware-software systems, quantization functions, and representation learning techniques to address this trade-off. Our results demonstrate that Signed Binarization is more accurate than binarization with the same number of non-zero weights. Detailed analysis indicates that signed binarization generates a smaller distribution of effectual (non-zero) parameters nested within a larger distribution of total parameters, both of the same type, for a DNN block. Finally, our approach achieves a 26% speedup on real hardware, doubles energy efficiency, and reduces density by 2.8x compared to binary methods for ResNet 18, presenting an alternative solution for deploying efficient models in resource-limited environments.

ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation

Graph Neural Networks (GNNs) have proven to be quite versatile for a variety of applications, including recommendation systems, fake news detection, drug discovery, and even computer vision. Due to the expanding size of graph-structured data, GNN models have also increased in complexity, leading to substantial latency issues. This is primarily attributed to the irregular structure of graph data and its access pattern into memory. The natural solution to reduce latency is to compress large GNNs into small GNNs. One way to do this is via knowledge distillation (KD). However, most KD approaches for GNNs only consider the outputs of the last layers and do not consider the outputs of the intermediate layers of the GNNs; these layers may contain important inductive biases indicated by the graph structure. To address this shortcoming, we propose a novel KD approach to GNN compression that we call Attention-Based Knowledge Distillation (ABKD). ABKD is a KD approach that uses attention to identify important intermediate teacher-student layer pairs and focuses on aligning their outputs. ABKD enables higher compression of GNNs with a smaller accuracy dropoff compared to existing KD approaches. On average, we achieve a 1.79% increase in accuracy with a 32.3x compression ratio on OGBN-Mag, a large graph dataset, compared to state-of-the-art approaches.

Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems

With the emergence of large foundational models, model-serving systems are becoming popular. In such a system, users send the queries to the server and specify the desired performance metrics (e.g., accuracy, latency, etc.). The server maintains a set of models (model zoo) in the back-end and serves the queries based on the specified metrics. This paper examines the security, specifically robustness against model extraction attacks, of such systems. Existing black-box attacks cannot be directly applied to extract a victim model, as models hide among the model zoo behind the inference serving interface, and attackers cannot identify which model is being used. An intermediate step is required to ensure that every input query gets the output from the victim model. To this end, we propose a query-efficient fingerprinting algorithm to enable the attacker to trigger any desired model consistently. We show that by using our fingerprinting algorithm, model extraction can have fidelity and accuracy scores within $1\%$ of the scores obtained if attacking in a single-model setting and up to $14.6\%$ gain in accuracy and up to $7.7\%$ gain in fidelity compared to the naive attack. Finally, we counter the proposed attack with a noise-based defense mechanism that thwarts fingerprinting by adding noise to the specified performance metrics. Our defense strategy reduces the attack's accuracy and fidelity by up to $9.8\%$ and $4.8\%$, respectively (on medium-sized model extraction). We show that the proposed defense induces a fundamental trade-off between the level of protection and system goodput, achieving configurable and significant victim model extraction protection while maintaining acceptable goodput ($>80\%$). We provide anonymous access to our code.

Subgraph Stationary Hardware-Software Inference Co-Design

A growing number of applications depend on Machine Learning (ML) functionality and benefits from both higher quality ML predictions and better timeliness (latency) at the same time. A growing body of research in computer architecture, ML, and systems software literature focuses on reaching better latency-accuracy tradeoffs for ML models. Efforts include compression, quantization, pruning, early-exit models, mixed DNN precision, as well as ML inference accelerator designs that minimize latency and energy, while preserving delivered accuracy. All of them, however, yield improvements for a single static point in the latency-accuracy tradeoff space. We make a case for applications that operate in dynamically changing deployment scenarios, where no single static point is optimal. We draw on a recently proposed weight-shared SuperNet mechanism to enable serving a stream of queries that uses (activates) different SubNets within this weight-shared construct. This creates an opportunity to exploit the inherent temporal locality with our proposed SubGraph Stationary (SGS) optimization. We take a hardware-software co-design approach with a real implementation of SGS in SushiAccel and the implementation of a software scheduler SushiSched controlling which SubNets to serve and what to cache in real-time. Combined, they are vertically integrated into SUSHI-an inference serving stack. For the stream of queries, SUSHI yields up to 25% improvement in latency, 0.98% increase in served accuracy. SUSHI can achieve up to 78.7% off-chip energy savings.

DynaQuant: Compressing Deep Learning Training Checkpoints via Dynamic Quantization

With the increase in the scale of Deep Learning (DL) training workloads in terms of compute resources and time consumption, the likelihood of encountering in-training failures rises substantially, leading to lost work and resource wastage. Such failures are typically offset by a checkpointing mechanism, which comes at the cost of storage and network bandwidth overhead. State-of-the-art approaches involve lossy model compression mechanisms, which induce a tradeoff between the resulting model quality (accuracy) and compression ratio. Delta compression is then also used to further reduce the overhead by only storing the difference between consecutive checkpoints. We make a key enabling observation that the sensitivity of model weights to compression varies during training, and different weights benefit from different quantization levels (ranging from retaining full precision to pruning). We propose (1) a non-uniform quantization scheme that leverages this variation, (2) an efficient search mechanism to dynamically adjust to the best quantization configurations, and (3) a quantization-aware delta compression mechanism that rearranges weights to minimize checkpoint differences, thereby maximizing compression. We instantiate these contributions in DynaQuant - a framework for DL workload checkpoint compression. Our experiments show that DynaQuant consistently achieves better tradeoff between accuracy and compression ratios compared to prior works, enabling a compression ratio up to 39x and withstanding up to 10 restores with negligible accuracy impact for fault-tolerant training. DynaQuant achieves at least an order of magnitude reduction in checkpoint storage overhead for training failure recovery as well as transfer learning use cases without any loss of accuracy

SuperFed: Weight Shared Federated Learning

Federated Learning (FL) is a well-established technique for privacy preserving distributed training. Much attention has been given to various aspects of FL training. A growing number of applications that consume FL-trained models, however, increasingly operate under dynamically and unpredictably variable conditions, rendering a single model insufficient. We argue for training a global family of models cost efficiently in a federated fashion. Training them independently for different tradeoff points incurs $O(k)$ cost for any k architectures of interest, however. Straightforward applications of FL techniques to recent weight-shared training approaches is either infeasible or prohibitively expensive. We propose SuperFed - an architectural framework that incurs $O(1)$ cost to co-train a large family of models in a federated fashion by leveraging weight-shared learning. We achieve an order of magnitude cost savings on both communication and computation by proposing two novel training mechanisms: (a) distribution of weight-shared models to federated clients, (b) central aggregation of arbitrarily overlapping weight-shared model parameters. The combination of these mechanisms is shown to reach an order of magnitude (9.43x) reduction in computation and communication cost for training a $5*10^{18}$-sized family of models, compared to independently training as few as $k = 9$ DNNs without any accuracy loss.

Signed Binary Weight Networks: Improving Efficiency of Binary Weight Networks by Exploiting Sparsity

Efficient inference of Deep Neural Networks (DNNs) is essential to making AI ubiquitous. Two important algorithmic techniques have shown promise for enabling efficient inference - sparsity and binarization. These techniques translate into weight sparsity and weight repetition at the hardware-software level allowing the deployment of DNNs with critically low power and latency requirements. We propose a new method called signed-binary networks to improve further efficiency (by exploiting both weight sparsity and weight repetition) while maintaining similar accuracy. Our method achieves comparable accuracy on ImageNet and CIFAR10 datasets with binary and can lead to $>69\%$ sparsity. We observe real speedup when deploying these models on general-purpose devices. We show that this high percentage of unstructured sparsity can lead to a further ~2x reduction in energy consumption on ASICs with respect to binary.

UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification

Machine Learning (ML) research has focused on maximizing the accuracy of predictive tasks. ML models, however, are increasingly more complex, resource intensive, and costlier to deploy in resource-constrained environments. These issues are exacerbated for prediction tasks with sequential classification on progressively transitioned stages with ''happens-before'' relation between them.We argue that it is possible to ''unfold'' a monolithic single multi-class classifier, typically trained for all stages using all data, into a series of single-stage classifiers. Each single-stage classifier can be cascaded gradually from cheaper to more expensive binary classifiers that are trained using only the necessary data modalities or features required for that stage. UnfoldML is a cost-aware and uncertainty-based dynamic 2D prediction pipeline for multi-stage classification that enables (1) navigation of the accuracy/cost tradeoff space, (2) reducing the spatio-temporal cost of inference by orders of magnitude, and (3) early prediction on proceeding stages. UnfoldML achieves orders of magnitude better cost in clinical settings, while detecting multi-stage disease development in real time. It achieves within 0.1% accuracy from the highest-performing multi-class baseline, while saving close to 20X on spatio-temporal cost of inference and earlier (3.5hrs) disease onset prediction. We also show that UnfoldML generalizes to image classification, where it can predict different level of labels (from coarse to fine) given different level of abstractions of a image, saving close to 5X cost with as little as 0.4% accuracy reduction.