Marconi: Prefix Caching for the Era of Hybrid LLMs

Hybrid models that combine the language modeling capabilities of Attention layers with the efficiency of Recurrent layers (e.g., State Space Models) have gained traction in practically supporting long contexts in Large Language Model serving. Yet, the unique properties of these models complicate the usage of complementary efficiency optimizations such as prefix caching that skip redundant computations across requests. Most notably, their use of in-place state updates for recurrent layers precludes rolling back cache entries for partial sequence overlaps, and instead mandates only exact-match cache hits; the effect is a deluge of (large) cache entries per sequence, most of which yield minimal reuse opportunities. We present Marconi, the first system that supports efficient prefix caching with Hybrid LLMs. Key to Marconi are its novel admission and eviction policies that more judiciously assess potential cache entries based not only on recency, but also on (1) forecasts of their reuse likelihood across a taxonomy of different hit scenarios, and (2) the compute savings that hits deliver relative to memory footprints. Across diverse workloads and Hybrid models, Marconi achieves up to 34.4$\times$ higher token hit rates (71.1% or 617 ms lower TTFT) compared to state-of-the-art prefix caching systems.

Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving

Machine learning (ML) inference platforms are tasked with balancing two competing goals: ensuring high throughput given many requests, and delivering low-latency responses to support interactive applications. Unfortunately, existing platform knobs (e.g., batch sizes) fail to ease this fundamental tension, and instead only enable users to harshly trade off one property for the other. This paper explores an alternate strategy to taming throughput-latency tradeoffs by changing the granularity at which inference is performed. We present Apparate, a system that automatically applies and manages early exits (EEs) in ML models, whereby certain inputs can exit with results at intermediate layers. To cope with the time-varying overhead and accuracy challenges that EEs bring, Apparate repurposes exits to provide continual feedback that powers several novel runtime monitoring and adaptation strategies. Apparate lowers median response latencies by 40.5-91.5% and 10.0-24.2% for diverse CV and NLP workloads, respectively, without affecting throughputs or violating tight accuracy constraints.

MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations

Camera orientations (i.e., rotation and zoom) govern the content that a camera captures in a given scene, which in turn heavily influences the accuracy of live video analytics pipelines. However, existing analytics approaches leave this crucial adaptation knob untouched, instead opting to only alter the way that captured images from fixed orientations are encoded, streamed, and analyzed. We present MadEye, a camera-server system that automatically and continually adapts orientations to maximize accuracy for the workload and resource constraints at hand. To realize this using commodity pan-tilt-zoom (PTZ) cameras, MadEye embeds (1) a search algorithm that rapidly explores the massive space of orientations to identify a fruitful subset at each time, and (2) a novel knowledge distillation strategy to efficiently (with only camera resources) select the ones that maximize workload accuracy. Experiments on diverse workloads show that MadEye boosts accuracy by 2.9-25.7% for the same resource usage, or achieves the same accuracy with 2-3.7x lower resource costs.

Marvolo: Programmatic Data Augmentation for Practical ML-Driven Malware Detection

Data augmentation has been rare in the cyber security domain due to technical difficulties in altering data in a manner that is semantically consistent with the original data. This shortfall is particularly onerous given the unique difficulty of acquiring benign and malicious training data that runs into copyright restrictions, and that institutions like banks and governments receive targeted malware that will never exist in large quantities. We present MARVOLO, a binary mutator that programmatically grows malware (and benign) datasets in a manner that boosts the accuracy of ML-driven malware detectors. MARVOLO employs semantics-preserving code transformations that mimic the alterations that malware authors and defensive benign developers routinely make in practice , allowing us to generate meaningful augmented data. Crucially, semantics-preserving transformations also enable MARVOLO to safely propagate labels from original to newly-generated data samples without mandating expensive reverse engineering of binaries. Further, MARVOLO embeds several key optimizations that keep costs low for practitioners by maximizing the density of diverse data samples generated within a given time (or resource) budget. Experiments using wide-ranging commercial malware datasets and a recent ML-driven malware detector show that MARVOLO boosts accuracies by up to 5%, while operating on only a small fraction (15%) of the potential input binaries.

Bamboo: Making Preemptible Instances Resilient for Affordable Training of Large DNNs

DNN models across many domains continue to grow in size, resulting in high resource requirements for effective training, and unpalatable (and often unaffordable) costs for organizations and research labs across scales. This paper aims to significantly reduce training costs with effective use of preemptible instances, i.e., those that can be obtained at a much cheaper price while idle, but may be preempted whenever requested by priority users. Doing so, however, requires new forms of resiliency and efficiency to cope with the possibility of frequent preemptions - a failure model that is drastically different from the occasional failures in normal cluster settings that existing checkpointing techniques target. We present Bamboo, a distributed system that tackles these challenges by introducing redundant computations into the training pipeline, i.e., whereby one node performs computations over not only its own layers but also over some layers in its neighbor. Our key insight is that training large models often requires pipeline parallelism where "pipeline bubbles" naturally exist. Bamboo carefully fills redundant computations into these bubbles, providing resilience at a low cost. Across a variety of widely used DNN models, Bamboo outperforms traditional checkpointing by 3.7x in training throughput, and reduces costs by 2.4x compared to a setting where on-demand instances are used.

GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge

Video analytics pipelines have steadily shifted to edge deployments to reduce bandwidth overheads and privacy violations, but in doing so, face an ever-growing resource tension. Most notably, edge-box GPUs lack the memory needed to concurrently house the growing number of (increasingly complex) models for real-time inference. Unfortunately, existing solutions that rely on time/space sharing of GPU resources are insufficient as the required swapping delays result in unacceptable frame drops and accuracy violations. We present model merging, a new memory management technique that exploits architectural similarities between edge vision models by judiciously sharing their layers (including weights) to reduce workload memory costs and swapping delays. Our system, GEMEL, efficiently integrates merging into existing pipelines by (1) leveraging several guiding observations about per-model memory usage and inter-layer dependencies to quickly identify fruitful and accuracy-preserving merging configurations, and (2) altering edge inference schedules to maximize merging benefits. Experiments across diverse workloads reveal that GEMEL reduces memory usage by up to 60.7%, and improves overall accuracy by 8-39% relative to time/space sharing alone.

Revelio: ML-Generated Debugging Queries for Distributed Systems

A major difficulty in debugging distributed systems lies in manually determining which of the many available debugging tools to use and how to query its logs. Our own study of a production debugging workflow confirms the magnitude of this burden. This paper explores whether a machine-learning model can assist developers in distributed systems debugging. We present Revelio, a debugging assistant which takes user reports and system logs as input, and outputs debugging queries that developers can use to find a bug's root cause. The key challenges lie in (1) combining inputs of different types (e.g., natural language reports and quantitative logs) and (2) generalizing to unseen faults. Revelio addresses these by employing deep neural networks to uniformly embed diverse input sources and potential queries into a high-dimensional vector space. In addition, it exploits observations from production systems to factorize query generation into two computationally and statistically simpler learning tasks. To evaluate Revelio, we built a testbed with multiple distributed applications and debugging tools. By injecting faults and training on logs and reports from 800 Mechanical Turkers, we show that Revelio includes the most helpful query in its predicted list of top-3 relevant queries 96% of the time. Our developer study confirms the utility of Revelio.

Boggart: Accelerating Retrospective Video Analytics via Model-Agnostic Ingest Processing

Delivering fast responses to retrospective queries on video datasets is difficult due to the large number of frames to consider and the high costs of running convolutional neural networks (CNNs) on each one. A natural solution is to perform a subset of the necessary computations ahead of time, as video is ingested. However, existing ingest-time systems require knowledge of the specific CNN that will be used in future queries -- a challenging requisite given the evergrowing space of CNN architectures and training datasets/methodologies. This paper presents Boggart, a retrospective video analytics system that delivers ingest-time speedups in a model-agnostic manner. Our underlying insight is that traditional computer vision (CV) algorithms are capable of performing computations that can be used to accelerate diverse queries with wide-ranging CNNs. Building on this, at ingest-time, Boggart carefully employs a variety of motion tracking algorithms to identify potential objects and their trajectories across frames. Then, at query-time, Boggart uses several novel techniques to collect the smallest sample of CNN results required to meet the target accuracy: (1) a clustering strategy to efficiently unearth the inevitable discrepancies between CV- and CNN-generated outputs, and (2) a set of accuracy-preserving propagation techniques to safely extend sampled results along each trajectory. Across many videos, CNNs, and queries Boggart consistently meets accuracy targets while using CNNs sparingly (on 3-54% of frames).

Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads

A graph neural network (GNN) enables deep learning on structured graph data. There are two major GNN training obstacles: 1) it relies on high-end servers with many GPUs which are expensive to purchase and maintain, and 2) limited memory on GPUs cannot scale to today's billion-edge graphs. This paper presents Dorylus: a distributed system for training GNNs. Uniquely, Dorylus can take advantage of serverless computing to increase scalability at a low cost. The key insight guiding our design is computation separation. Computation separation makes it possible to construct a deep, bounded-asynchronous pipeline where graph and tensor parallel tasks can fully overlap, effectively hiding the network latency incurred by Lambdas. With the help of thousands of Lambda threads, Dorylus scales GNN training to billion-edge graphs. Currently, for large graphs, CPU servers offer the best performance-per-dollar over GPU servers. Just using Lambdas on top of CPU servers offers up to 2.75x more performance-per-dollar than training only with CPU servers. Concretely, Dorylus is 1.22x faster and 4.83x cheaper than GPU servers for massive sparse graphs. Dorylus is up to 3.8x faster and 10.7x cheaper compared to existing sampling-based systems.