Skip to content
conftrace_

wall-clock latency

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

computational throughput (1) nlp optimization (1) computational latency (1) framework overhead (1) model latency (1) deep learning framework (1) hardware acceleration (1) inference efficiency (1)

Papers

The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment EMNLP 2023