How does the accuracy-throughput trade-off of Llama3-70B and Codestral-34B compare when deployed on heterogene

Abstract

Abstract: This paper proposes a neural architecture search (NAS) method for split computing. Split computing is an emerging machine-learning inference technique that addresses the privacy and latency challenges of deploying deep learning in IoT systems. In split computing, neural network models are separated and cooperatively processed using edge servers and IoT devices via networks. Thus, the architecture of the neural network model significantly impacts the communication payload size, model accuracy, and computational load. In this paper, we address the challenge of optimizing neural network architect

Research Question

How does the accuracy-throughput trade-off of Llama3-70B and Codestral-34B compare when deployed on heterogeneous edge devices (e.g., mobile, embedded) for HumanEval-hard, and what optimizations best maintain accuracy at minimal latency?

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