From words to watts: Benchmarking the energy costs of large language model inference
Large language models (LLMs) have exploded in popularity due to their new generative
capabilities that go far beyond prior state-of-the-art. These technologies are increasingly …
capabilities that go far beyond prior state-of-the-art. These technologies are increasingly …
Sustainable supercomputing for AI: GPU power capping at HPC scale
As research and deployment of AI grows, the computational burden to support and sustain
its progress inevitably does too. To train or fine-tune state-of-the-art models in NLP …
its progress inevitably does too. To train or fine-tune state-of-the-art models in NLP …
Towards Green AI. A methodological survey of the scientific literature
E Barbierato, A Gatti - IEEE Access, 2024 - ieeexplore.ieee.org
The pervasive deployment of Deep Learning models has recently prompted apprehensions
regarding their ecological footprint, owing to the exorbitant levels of energy consumption …
regarding their ecological footprint, owing to the exorbitant levels of energy consumption …
Energy Concerns with HPC Systems and Applications
For various reasons including those related to climate changes,{\em energy} has become a
critical concern in all relevant activities and technical designs. For the specific case of …
critical concern in all relevant activities and technical designs. For the specific case of …
TRAWL: Tensor Reduced and Approximated Weights for Large Language Models
Large language models (LLMs) have fundamentally transformed artificial intelligence,
catalyzing recent advancements while imposing substantial environmental and …
catalyzing recent advancements while imposing substantial environmental and …
An Analysis of Energy Requirement for Computer Vision Algorithms
D Edelman, S Samsi, J McDonald… - 2023 IEEE High …, 2023 - ieeexplore.ieee.org
The energy requirements of neural network learning are growing at a rapid rate. Increased
energy demands have caused a global need to seek ways to improve energy efficiency of …
energy demands have caused a global need to seek ways to improve energy efficiency of …
Report from Dagstuhl Seminar 23352: Integrating HPC, AI, and Workflows for Scientific Data Analysis
The Dagstuhl Seminar 23352, titled “Integrating HPC, AI, and Workflows for Scientific Data
Analysis,” held from August 27 to September 1, 2023, was a significant event focusing on the …
Analysis,” held from August 27 to September 1, 2023, was a significant event focusing on the …
[PDF][PDF] Integrating HPC, AI, and Workflows for Scientific Data Analysis
ABSTRACT The Dagstuhl Seminar 23352, titled “Integrating HPC, AI, and Workflows for
Scientific Data Analysis,” held from August 27 to September 1, 2023, was a significant event …
Scientific Data Analysis,” held from August 27 to September 1, 2023, was a significant event …
Integrating HPC, AI, and Workflows for Scientific Data Analysis: report from Dagstuhl Seminar 23352
The Dagstuhl Seminar 23352, titled “Integrating HPC, AI, and Workflows for Scientific Data
Analysis,” held from August 27 to September 1, 2023, was a significant event focusing on the …
Analysis,” held from August 27 to September 1, 2023, was a significant event focusing on the …