An official website of the United States government
Tiny machine learning (TinyML) applications increasingly operate in dynamically changing deployment scenarios, requiring optimization for both accuracy and latency. Existing methods mainly target a single point in the accuracy/latency tradeoff space, which is insufficient as no single static point can be optimal under variable conditions. We draw on a recently proposed weight-shared SuperNet mechanism to enable serving a stream of queries that activates different SubNets within a SuperNet. This creates an opportunity to exploit the inherent temporal locality of different queries that use the same SuperNet. We propose a hardware–software co-design called SUSHI that introduces a novel SubGraph Stationary optimization. SUSHI consists of a novel field-programmable gate array implementation and a software scheduler that controls which SubNets to serve and which SubGraph to cache in real time. SUSHI yields up to a 32% improvement in latency, 0.98% increase in served accuracy, and achieves up to 78.7% off-chip energy saved across several neural network architectures.
more »
« less
This content will become publicly available on April 28, 2026
SuperServe: fine-grained inference serving for unpredictable workloads
The increasing deployment of ML models on the critical path of production applications requires ML inference serving systems to serve these models under unpredictable and bursty request arrival rates. Serving many models under such conditions requires a careful balance between each application's latency and accuracy requirements and the overall efficiency of utilization of scarce resources. Faced with this tension, state-of-the-art systems either choose a single model representing a static point in the latency-accuracy tradeoff space to serve all requests or incur latency target violations by loading specific models on the critical path of request serving. Our work instead resolves this tension through a resource-efficient serving of the entire range of models spanning the latency-accuracy tradeoff space. Our novel mechanism, SubNetAct, achieves this by carefully inserting specialized control-flow operators in pre-trained, weight-shared super-networks. These operators enable SubNetAct to dynamically route a request through the network to actuate a specific model that meets the request's latency and accuracy target. Thus, SubNetAct can serve a vastly higher number of models than prior systems while requiring upto 2.6\texttimes{} lower memory. More crucially, SubNetAct's near-instantaneous actuation of a wide-range of models unlocks the design space of fine-grained, reactive scheduling policies. We design one such extremely effective policy, SlackFit, and instantiate both SubNetAct and Slack-Fit in a real system, SuperServe. On real-world traces derived from a Microsoft workload, SuperServe achieves 4.67\% higher accuracy for the same latency targets and 2.85\texttimes{} higher latency target attainment for the same accuracy.
more »
« less
- Award ID(s):
- 2420977
- PAR ID:
- 10656321
- Publisher / Repository:
- USENIX Association
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Begnum, Kyrre; Border, Charles (Ed.)With the increasing popularity of large deep learning model serving workloads, there is a pressing need to reduce the energy consumption of a model-serving cluster while maintaining satisfied throughput or model-serving latency requirements. Model multiplexing approaches such as model parallelism, model placement, replication, and batching aim to optimize the model-serving performance. However, they fall short of leveraging the GPU frequency scaling opportunity for power saving. In this paper, we demonstrate (1) the benefits of GPU frequency scaling in power saving for model serving; and (2) the necessity for co-design and optimization of fine grained model multiplexing and GPU frequency scaling. We explore the co-design space and present a novel power-aware model-serving system, μ-Serve. μ-Serve is a model-serving framework that optimizes the power consumption and model serving latency/throughput of serving multiple ML models efficiently in a homogeneous GPU cluster. Evaluation results on production workloads show that μ-Serve achieves 1.2–2.6× power saving by dynamic GPU frequency scaling (up to 61% reduction) without SLO attainment violations.more » « less
-
Begnum, Kyrre; Border, Charles (Ed.)With the increasing popularity of large deep learning model-serving workloads, there is a pressing need to reduce the energy consumption of a model-serving cluster while maintaining satisfied throughput or model-serving latency requirements. Model multiplexing approaches such as model parallelism, model placement, replication, and batching aim to optimize the model-serving performance. However, they fall short of leveraging the GPU frequency scaling opportunity for power saving. In this paper, we demonstrate (1) the benefits of GPU frequency scaling in power saving for model serving; and (2) the necessity for co-design and optimization of fine-grained model multiplexing and GPU frequency scaling. We explore the co-design space and present a novel power-aware model-serving system, μ-Serve. μ-Serve is a model-serving framework that optimizes the power consumption and model-serving latency/throughput of serving multiple ML models efficiently in a homogeneous GPU cluster. Evaluation results on production workloads show that μ-Serve achieves 1.2–2.6× power saving by dynamic GPU frequency scaling (up to 61% reduction) without SLO attainment violations.more » « less
-
The success of machine learning has prospered Machine-Learning-as-a-Service (MLaaS) - deploying trained machine learning (ML) models in cloud to provide low latency inference services at scale. To meet latency Service-Level-Objective (SLO), judicious parallelization at both request and operation levels is utterly important. However, existing ML systems (e.g., Tensorflow) and cloud ML serving platforms (e.g., SageMaker) are SLO-agnostic and rely on users to manually configure the parallelism. To provide low latency ML serving, this paper proposes a swift machine learning serving scheduling framework with a novel Region-based Reinforcement Learning (RRL) approach. RRL can efficiently identify the optimal parallelism configuration under different workloads by estimating performance of similar configurations with that of the known ones. We both theoretically and experimentally show that the RRL approach can outperform state-of-the-art approaches by finding near optimal solutions over 8 times faster while reducing inference latency up to 79.0% and reducing SLO violation up to 49.9%.more » « less
-
Low-latency and low-power edge AI is crucial for Virtual Reality and Augmented Reality applications. Recent advances demonstrate that hybrid models, combining convolution layers (CNN) and transformers (ViT), often achieve a superior accuracy/performance tradeoff on various computer vision and machine learning (ML) tasks. However, hybrid ML models can present system challenges for latency and energy efficiency due to their diverse nature in dataflow and memory access patterns. In this work, we leverage architecture heterogeneity from Neural Processing Units (NPU) and Compute-In-Memory (CIM) and explore diverse execution schemas to efficiently execute these hybrid models. We introduce H4H-NAS, a two-stage Neural Architecture Search (NAS) framework to automate the design of efficient hybrid CNN/ViT models for heterogeneous edge systems featuring both NPU and CIM. We propose a two-phase incremental supernet training in our NAS framework to resolve gradient conflicts between sampled subnets caused by different types of blocks in a hybrid model search space. Our H4H-NAS approach is also powered by a performance estimator built with NPU performance results measured on real silicon, and CIM performance based on industry IPs. H4H-NAS searches hybrid CNN-ViT models with fine granularity and achieves significant (up to 1.34%) top-1 accuracy improvement on ImageNet. Moreover, results from our algorithm/hardware co-design reveal up to 56.08% overall latency and 41.72% energy improvements by introducing heterogeneous computing over baseline solutions. Overall, our framework guides the design of hybrid network architectures and system architectures for NPU+CIM heterogeneous systems.more » « less
