Picture for ChonLam Lao

ChonLam Lao

Harvard University

HawkVision: Low-Latency Modeless Edge AI Serving

Add code
May 29, 2024
Viaarxiv icon

THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic Compression

Add code
Feb 16, 2023
Viaarxiv icon

Efficient Data-Plane Memory Scheduling for In-Network Aggregation

Add code
Jan 17, 2022
Figure 1 for Efficient Data-Plane Memory Scheduling for In-Network Aggregation
Figure 2 for Efficient Data-Plane Memory Scheduling for In-Network Aggregation
Figure 3 for Efficient Data-Plane Memory Scheduling for In-Network Aggregation
Figure 4 for Efficient Data-Plane Memory Scheduling for In-Network Aggregation
Viaarxiv icon