MétaCan
Menu
Back to cohort

Benchmarking Emerging Deep Learning Quantization Methods for Energy Efficiency

2024· article· en· W4401723357 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Neural Network Applications
Canadian institutionsDalhousie University
Fundersnot available
KeywordsBenchmarkingQuantization (signal processing)Computer scienceDeep learningEfficient energy useArtificial intelligenceElectrical engineeringEngineeringComputer visionBusiness

Abstract

fetched live from OpenAlex

In the era of generative artificial intelligence (AI), the quest for energy-efficient AI models is increasing. The increasing size of recent AI models has led to quantization techniques that reduce large models' computing and memory requirements. This study aims to compare the energy consumption of five quantization methods, viz. Gradient-based Post-Training Quantization (GPTQ),Activation-aware Weight Quantization (AWQ), GPT-Generated Model Language (GGML), GPT-Generated Unified Format (GGUF), and Bits and Bytes (BNB). We benchmark and analyze the energy efficiency of these commonly used quantization methods during inference. This preliminary exploration found that GGML and its successor GGUF were the most energy-efficient quantization methods. Our findings reveal significant variability in energy profiles across methods, challenging the notion that lower precision universally improves efficiency. The results underscore the need to benchmark quantization techniques from an energy perspective beyond just model compression. Our findings could guide the selection of models using quantization techniques and the development of new quantization techniques that prioritize energy efficiency, potentially leading to more environmentally friendly AI deployments.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.849
Threshold uncertainty score0.376

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.022
GPT teacher head0.359
Teacher spread0.337 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Quick stats

Citations17
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicAdvanced Neural Network ApplicationsFrench-language works237,207