WattLayer is a layer-wise energy estimation model achieving 19.6% median error on over 100k layers from 295 architectures across 3 tasks and 3 platforms, with generalization to new tasks via shared layers.
Sustainable ai: Environmental implications, challenges and opportunities
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 2polarities
background 2representative citing papers
Execution-idle accounts for 19.7% of GPU execution time and 10.7% of energy in a large cluster, motivating power management that treats it as a distinct operating state.
MRKL is a modular neuro-symbolic architecture that integrates LLMs with external knowledge and discrete reasoning to overcome limitations of pure neural language models.
CWM combines dynamic programming and heuristics to achieve 42% median carbon cost reduction over CaWoSched for workflows when deadline is twice the carbon-agnostic makespan.
LLM inference should be reframed and evaluated as energy-to-token production with a Token Production Function that accounts for power, cooling, and efficiency ceilings.
A publicly released conditional hierarchical VAE generates high-resolution multi-pathology ECGs and raises downstream AUROC by up to 2% over GAN baselines in transfer-learning tests.
citing papers explorer
-
WattLayer: Get Layers Right to Estimate Inference Energy of Neural Networks
WattLayer is a layer-wise energy estimation model achieving 19.6% median error on over 100k layers from 295 architectures across 3 tasks and 3 platforms, with generalization to new tasks via shared layers.
-
The Energy Cost of Execution-Idle in GPU Clusters
Execution-idle accounts for 19.7% of GPU execution time and 10.7% of energy in a large cluster, motivating power management that treats it as a distinct operating state.
-
MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning
MRKL is a modular neuro-symbolic architecture that integrates LLMs with external knowledge and discrete reasoning to overcome limitations of pure neural language models.
-
Carbon-Aware Mapping and Scheduling for Deadline-Constrained Workflows
CWM combines dynamic programming and heuristics to achieve 42% median carbon cost reduction over CaWoSched for workflows when deadline is twice the carbon-agnostic makespan.
-
Position: LLM Inference Should Be Evaluated as Energy-to-Token Production
LLM inference should be reframed and evaluated as energy-to-token production with a Token Production Function that accounts for power, cooling, and efficiency ceilings.
-
Conditional Electrocardiogram Generation Using Hierarchical Variational Autoencoders
A publicly released conditional hierarchical VAE generates high-resolution multi-pathology ECGs and raises downstream AUROC by up to 2% over GAN baselines in transfer-learning tests.