activity
20182020
most citedDynamic Space-Time Scheduling for GPU Inference

27 citations · 31 across the 3 of their papers we have counts for

collaborators

5 papers

cs.DB2020

Towards Scalable Dataframe Systems

Devin Petersohn, Stephen Macke, Doris Xin +7

Dataframes are a popular abstraction to represent, prepare, and analyze data. Despite the remarkable success of dataframe libraries in Rand Python, dataframes face performance issu…

cs.CV2019

Pay Attention to Convolution Filters: Towards Fast and Accurate Fine-Grained Transfer Learning

Xiangxi Mo, Ruizhe Cheng, Tianyi Fang

We propose an efficient transfer learning method for adapting ImageNet pre-trained Convolutional Neural Network (CNN) to fine-grained image classification task. Conventional transf…

cs.DC20194 cited

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…

cs.DC201827 cited

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…

cs.DC2018

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…