"Through a strong and close partnership with Intel, we have helped our customers accelerate their online service greatly with Intel® technology. By leveraging and integrating the key features of Intel® Neural Compressor and Intel® Extension for Transformers* into Alibaba Cloud* PAI-Blade, we offer extremely high performance and reduce the total cost of ownership (TCO). These tools provide a high-performance solution for model optimization and optimized-aware inference, which makes it extremely easy for PAI-Blade to adopt optimizations like int8 for better performance without accuracy loss. We believe our ongoing collaboration with Intel will bring more benefits to AI workloads and services."
— Shen Li, staff algorithm engineer, Alibaba Cloud
Optimization of Intel® AI Solutions for Alibaba Cloud Qwen2 LLMs
Intel® Advanced Matrix Extensions Enhances AI Inference Performance