Search Results for author:
Found 5 papers, 2 papers with code
Tiered Pruning for Efficient Differentialble Inference-Aware Neural Architecture Search
We propose three novel pruning techniques to improve the cost and results of inference-aware Differentiable Neural Architecture Search (DNAS).
GPUNet: Searching the Deployable Convolution Neural Networks for GPUs
This paper intends to expedite the model customization with a model hub that contains the optimized models tiered by their inference latency using Neural Architecture Search (NAS).
Ranked #2 on
Neural Architecture Search
on ImageNet
Searching the Deployable Convolution Neural Networks for GPUs
To achieve this goal, we build a distributed NAS system to search on a novel search space that consists of prominent factors to impact latency and accuracy.
Pay Attention when Required
Transformer-based models consist of interleaved feed-forward blocks - that capture content meaning, and relatively more expensive self-attention blocks - that capture context meaning.
Ranked #1 on
Language Modelling
on enwiki8
Optimizing Multi-GPU Parallelization Strategies for Deep Learning Training
This work explores hybrid parallelization, where each data parallel worker is comprised of more than one device, across which the model dataflow graph (DFG) is split using MP.
