176 citations · 699 across the 41 of their papers we have counts for
9 papers · 1 filter
Hindsight Logging for Model Training
Rolando Garcia, Eric Liu, Vikram Sreekanti +5
In modern Machine Learning, model training is an iterative, experimental process that can consume enormous computation resources and developer time. To aid in that process, experie…
HyperSched: Dynamic Resource Reallocation for Model Development on a Deadline
Richard Liaw, Romil Bhardwaj, Lisa Dunlap +4
Prior research in resource scheduling for machine learning training workloads has largely focused on minimizing job completion times. Commonly, these model training workloads colle…
Cloudburst: Stateful Functions-as-a-Service
Vikram Sreekanti, Chenggang Wu, Xiayue Charles Lin +5
Function-as-a-Service (FaaS) platforms and "serverless" cloud computing are becoming increasingly popular. Current FaaS offerings are targeted at stateless functions that do minima…
The OoO VLIW JIT Compiler for GPU Inference
Paras Jain, Xiangxi Mo, Ajay Jain +3
Current trends in Machine Learning~(ML) inference on hardware accelerated devices (e.g., GPUs, TPUs) point to alarmingly low utilization. As ML inference is increasingly time-bound…
Dynamic Space-Time Scheduling for GPU Inference
Paras Jain, Xiangxi Mo, Ajay Jain +5
Serving deep neural networks in latency critical interactive settings often requires GPU acceleration. However, the small batch sizes typical in online inference results in poor GP…
InferLine: ML Prediction Pipeline Provisioning and Management for Tight Latency Objectives
Daniel Crankshaw, Gur-Eyal Sela, Corey Zumar +4
Serving ML prediction pipelines spanning multiple models and hardware accelerators is a key challenge in production machine learning. Optimally configuring these pipelines to meet…