cs.AI updates on arXiv.org 10小时前
Serving LLMs in HPC Clusters: A Comparative Study of Qualcomm Cloud AI 100 Ultra and High-Performance GPUs
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文对Qualcomm Cloud AI 100 Ultra (QAic)加速器进行基准测试,评估其在大型语言模型推理中的能效和性能,与NVIDIA和AMD的GPU相比表现良好,为NRP平台的高性能计算应用提供潜在价值。

arXiv:2507.00418v1 Announce Type: cross Abstract: This study presents a benchmarking analysis of the Qualcomm Cloud AI 100 Ultra (QAic) accelerator for large language model (LLM) inference, evaluating its energy efficiency (throughput per watt) and performance against leading NVIDIA (A100, H200) and AMD (MI300A) GPUs within the National Research Platform (NRP) ecosystem. A total of 15 open-source LLMs, ranging from 117 million to 90 billion parameters, are served using the vLLM framework. The QAic inference cards appears to be energy efficient and performs well in the energy efficiency metric in most cases. The findings offer insights into the potential of the Qualcomm Cloud AI 100 Ultra for high-performance computing (HPC) applications within the National Research Platform (NRP).

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

QAic加速器 LLM推理 能效 高性能计算
相关文章