Hierarchical Autoscaling for Large Language Model Serving with Chiron

Large language model (LLM) serving is becoming an increasingly important workload for cloud providers. Based on performance SLO requirements, LLM inference requests can be divided into (a) interactive requests that have tight SLOs in the order of seconds, and (b) batch requests that have relaxed SLO in the order of minutes to hours. These SLOs can degrade based on the arrival rates, multiplexing, and configuration parameters, thus necessitating the use of resource autoscaling on serving instances and their batch sizes. However, previous autoscalers for LLM serving do not consider request SLOs leading to unnecessary scaling and resource under-utilization. To address these limitations, we introduce Chiron, an autoscaler that uses the idea of hierarchical backpressure estimated using queue size, utilization, and SLOs. Our experiments show that Chiron achieves up to 90% higher SLO attainment and improves GPU efficiency by up to 70% compared to existing solutions.

Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction

Large language models (LLMs) have been driving a new wave of interactive AI applications across numerous domains. However, efficiently serving LLM inference requests is challenging due to their unpredictable execution times originating from the autoregressive nature of generative models. Existing LLM serving systems exploit first-come-first-serve (FCFS) scheduling, suffering from head-of-line blocking issues. To address the non-deterministic nature of LLMs and enable efficient interactive LLM serving, we present a speculative shortest-job-first (SSJF) scheduler that uses a light proxy model to predict LLM output sequence lengths. Our open-source SSJF implementation does not require changes to memory management or batching strategies. Evaluations on real-world datasets and production workload traces show that SSJF reduces average job completion times by 30.5-39.6% and increases throughput by 2.2-3.6x compared to FCFS schedulers, across no batching, dynamic batching, and continuous batching settings.

Watch Out for the Safety-Threatening Actors: Proactively Mitigating Safety Hazards

Despite the successful demonstration of autonomous vehicles (AVs), such as self-driving cars, ensuring AV safety remains a challenging task. Although some actors influence an AV's driving decisions more than others, current approaches pay equal attention to each actor on the road. An actor's influence on the AV's decision can be characterized in terms of its ability to decrease the number of safe navigational choices for the AV. In this work, we propose a safety threat indicator (STI) using counterfactual reasoning to estimate the importance of each actor on the road with respect to its influence on the AV's safety. We use this indicator to (i) characterize the existing real-world datasets to identify rare hazardous scenarios as well as the poor performance of existing controllers in such scenarios; and (ii) design an RL based safety mitigation controller to proactively mitigate the safety hazards those actors pose to the AV. Our approach reduces the accident rate for the state-of-the-art AV agent(s) in rare hazardous scenarios by more than 70%.

Watch out for the risky actors: Assessing risk in dynamic environments for safe driving

Driving in a dynamic environment that consists of other actors is inherently a risky task as each actor influences the driving decision and may significantly limit the number of choices in terms of navigation and safety plan. The risk encountered by the Ego actor depends on the driving scenario and the uncertainty associated with predicting the future trajectories of the other actors in the driving scenario. However, not all objects pose a similar risk. Depending on the object's type, trajectory, position, and the associated uncertainty with these quantities; some objects pose a much higher risk than others. The higher the risk associated with an actor, the more attention must be directed towards that actor in terms of resources and safety planning. In this paper, we propose a novel risk metric to calculate the importance of each actor in the world and demonstrate its usefulness through a case study.

BayesPerf: Minimizing Performance Monitoring Errors Using Bayesian Statistics

Hardware performance counters (HPCs) that measure low-level architectural and microarchitectural events provide dynamic contextual information about the state of the system. However, HPC measurements are error-prone due to non determinism (e.g., undercounting due to event multiplexing, or OS interrupt-handling behaviors). In this paper, we present BayesPerf, a system for quantifying uncertainty in HPC measurements by using a domain-driven Bayesian model that captures microarchitectural relationships between HPCs to jointly infer their values as probability distributions. We provide the design and implementation of an accelerator that allows for low-latency and low-power inference of the BayesPerf model for x86 and ppc64 CPUs. BayesPerf reduces the average error in HPC measurements from 40.1% to 7.6% when events are being multiplexed. The value of BayesPerf in real-time decision-making is illustrated with a simple example of scheduling of PCIe transfers.

ML-driven Malware that Targets AV Safety

Ensuring the safety of autonomous vehicles (AVs) is critical for their mass deployment and public adoption. However, security attacks that violate safety constraints and cause accidents are a significant deterrent to achieving public trust in AVs, and that hinders a vendor's ability to deploy AVs. Creating a security hazard that results in a severe safety compromise (for example, an accident) is compelling from an attacker's perspective. In this paper, we introduce an attack model, a method to deploy the attack in the form of smart malware, and an experimental evaluation of its impact on production-grade autonomous driving software. We find that determining the time interval during which to launch the attack is{ critically} important for causing safety hazards (such as collisions) with a high degree of success. For example, the smart malware caused 33X more forced emergency braking than random attacks did, and accidents in 52.6% of the driving simulations.

Inductive Bias-driven Reinforcement Learning For Efficient Schedules in Heterogeneous Clusters

The problem of scheduling of workloads onto heterogeneous processors (e.g., CPUs, GPUs, FPGAs) is of fundamental importance in modern datacenters. Most current approaches rely on building application/system-specific heuristics that have to be reinvented on a case-by-case basis. This can be prohibitively expensive and is untenable going forward. In this paper, we propose a domain-driven reinforcement learning (RL) model for scheduling that can be broadly applied to a large class of heterogeneous processors. The key novelty of our approach is (i) the RL model; and (ii) the significant reduction of training-data (using domain knowledge) and -time (using sampling based end-to-end gradient propagation). We demonstrate the approach using real world GPU and FPGA accelerated applications to produce scheduling policies that significantly outperform hand-tuned heuristics.

Live Forensics for Distributed Storage Systems

We present Kaleidoscope an innovative system that supports live forensics for application performance problems caused by either individual component failures or resource contention issues in large-scale distributed storage systems. The design of Kaleidoscope is driven by our study of I/O failures observed in a peta-scale storage system anonymized as PetaStore. Kaleidoscope is built on three key features: 1) using temporal and spatial differential observability for end-to-end performance monitoring of I/O requests, 2) modeling the health of storage components as a stochastic process using domain-guided functions that accounts for path redundancy and uncertainty in measurements, and, 3) observing differences in reliability and performance metrics between similar types of healthy and unhealthy components to attribute the most likely root causes. We deployed Kaleidoscope on PetaStore and our evaluation shows that Kaleidoscope can run live forensics at 5-minute intervals and pinpoint the root causes of 95.8% of real-world performance issues, with negligible monitoring overhead.

ML-based Fault Injection for Autonomous Vehicles: A Case for Bayesian Fault Injection

The safety and resilience of fully autonomous vehicles (AVs) are of significant concern, as exemplified by several headline-making accidents. While AV development today involves verification, validation, and testing, end-to-end assessment of AV systems under accidental faults in realistic driving scenarios has been largely unexplored. This paper presents DriveFI, a machine learning-based fault injection engine, which can mine situations and faults that maximally impact AV safety, as demonstrated on two industry-grade AV technology stacks (from NVIDIA and Baidu). For example, DriveFI found 561 safety-critical faults in less than 4 hours. In comparison, random injection experiments executed over several weeks could not find any safety-critical faults

P-HGRMS: A Parallel Hypergraph Based Root Mean Square Algorithm for Image Denoising

This paper presents a parallel Salt and Pepper (SP) noise removal algorithm in a grey level digital image based on the Hypergraph Based Root Mean Square (HGRMS) approach. HGRMS is generic algorithm for identifying noisy pixels in any digital image using a two level hierarchical serial approach. However, for SP noise removal, we reduce this algorithm to a parallel model by introducing a cardinality matrix and an iteration factor, k, which helps us reduce the dependencies in the existing approach. We also observe that the performance of the serial implementation is better on smaller images, but once the threshold is achieved in terms of image resolution, its computational complexity increases drastically. We test P-HGRMS using standard images from the Berkeley Segmentation dataset on NVIDIAs Compute Unified Device Architecture (CUDA) for noise identification and attenuation. We also compare the noise removal efficiency of the proposed algorithm using Peak Signal to Noise Ratio (PSNR) to the existing approach. P-HGRMS maintains the noise removal efficiency and outperforms its sequential counterpart by 6 to 18 times (6x - 18x) in computational efficiency.