PowerInfer Dynamic Hot Neuron Thresholding vs Static Inference in LLaMA-70B Code Generation

Abstract

Abstract: This report synthesises findings from 11 peer-reviewed papers addressing the following research question: How does PowerInfer's dynamic hot neuron threshold adjustment compare to static inference methods in terms of throughput and memory efficiency when applied to LLaMA-70B on the HumanEval code. This paper introduces PowerInfer, a high-speed Large Language Model (LLM) inference engine on a personal computer (PC) equipped with a single consumer-grade GPU. The key principle underlying the design of PowerInfer is exploiting the high locality inherent in LLM inference. 10 claims were extracted from source literature; 10 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.7/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does PowerInfer's dynamic hot neuron threshold adjustment compare to static inference methods in terms of throughput and memory efficiency when applied to LLaMA-70B on the HumanEval code generation benchmark?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance