REVIEW 3 cited by
Inference performance evaluation for LLMs on edge devices with a novel benchmarking framework and metric
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Inference performance evaluation for LLMs on edge devices with a novel benchmarking framework and metric
read the original abstract
With the significant success achieved by large language models (LLMs) like LLaMA, edge computing-based LLM inference services for mobile and PC are in high demand for data privacy. However, different edge platforms have different hardware characteristics and the large demand for memory capacity and bandwidth makes it very challenging to deploy and benchmark LLMs on edge devices. In this paper, we introduce a benchmarking tool named ELIB (edge LLM inference benchmarking) to evaluate LLM inference performance of different edge platforms, and propose a novel metric named MBU to indicate the percentage of the theoretically efficient use of available memory bandwidth for a specific model running on edge hardware to optimize memory usage. We deploy ELIB on three edge platforms and benchmark using five quantized models to optimize MBU in combination with other metrics such as FLOPS, throughput, latency and accuracy. And we analyze the results to derive the key factors, constraints, unpredictability in optimizing MBU that can guide deploying LLMs on more edge platforms.
Forward citations
Cited by 3 Pith papers
-
Think Before You Grid-Search: Floor-First Triage for LLM Serving
A five-dimensional resource-vector floor model computes latency bounds and capacity walls for LLM serving, predicting when TP16 or EP16+DP attention layouts dominate based on operating point.
-
Think Before You Grid-Search: Floor-First Triage for LLM Serving
LLM serving should triage by five-resource analytical floors and wall ordering, not grid search; on 16×H20, TP16 is capacity-capped at ~70 while EP+DP attention reaches ~644 concurrent 8K requests.
-
CATS: Cascaded Adaptive Tree Speculation for Memory-Limited LLM Inference Acceleration
CATS achieves up to 5.08x wall-clock speedup for LLM generation on edge devices via memory-matched cascaded tree speculation, outperforming prior methods by 1.45x with no quality loss.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.