Efficient LLM Inference on CPUs
This work addresses the problem of efficient LLM deployment for users with CPU-based systems, though it appears incremental as it builds on existing quantization and optimization techniques.
The paper tackles the challenge of deploying large language models (LLMs) on CPUs by proposing an approach that includes automatic INT4 weight-only quantization and optimized kernels, resulting in extreme inference efficiency demonstrated on models like Llama2 and GPT-NeoX.
Large language models (LLMs) have demonstrated remarkable performance and tremendous potential across a wide range of tasks. However, deploying these models has been challenging due to the astronomical amount of model parameters, which requires a demand for large memory capacity and high memory bandwidth. In this paper, we propose an effective approach that can make the deployment of LLMs more efficiently. We support an automatic INT4 weight-only quantization flow and design a special LLM runtime with highly-optimized kernels to accelerate the LLM inference on CPUs. We demonstrate the general applicability of our approach on popular LLMs including Llama2, Llama, GPT-NeoX, and showcase the extreme inference efficiency on CPUs. The code is publicly available at: https://github.com/intel/intel-extension-for-transformers.