Search Results for author:
Found 5 papers, 1 papers with code
AttMEMO : Accelerating Transformers with Memoization on Big Memory Systems
Transformer models gain popularity because of their superior inference accuracy and inference throughput.
Hydra: Hybrid Server Power Model
Due to increasing software and hardware heterogeneity, we observed that there is no single power model that works the best for all server conditions.
Revealing Secrets From Pre-trained Models
In this paper, we show a new observation that pre-trained models and fine-tuned models have significantly high similarities in weight values.
Characterization of Semantic Segmentation Models on Mobile Platforms for Self-Navigation in Disaster-Struck Zones
In this paper, we characterize a number of state-of-the-art FCN models on mobile embedded platforms for self-navigation at these sites containing extremely irregular obstacles.
Tango: A Deep Neural Network Benchmark Suite for Various Accelerators
To provide a more scalable evaluation environment, we propose a new DNN benchmark suite that can run on any platform that supports CUDA and OpenCL.
