VcLLM: Video Codecs are Secretly Tensor Codecs
This addresses memory and bandwidth limitations for LLM developers, offering a novel solution with broad applicability.
The paper tackles the memory and communication bottlenecks in large language models (LLMs) by proposing to repurpose video codecs as tensor codecs, achieving state-of-the-art compression efficiency and enabling training and inference on consumer-grade GPUs.
As the parameter size of large language models (LLMs) continues to expand, the need for a large memory footprint and high communication bandwidth have become significant bottlenecks for the training and inference of LLMs. To mitigate these bottlenecks, various tensor compression techniques have been proposed to reduce the data size, thereby alleviating memory requirements and communication pressure. Our research found that video codecs, despite being originally designed for compressing videos, show excellent efficiency when compressing various types of tensors. We demonstrate that video codecs can be versatile and general-purpose tensor codecs while achieving the state-of-the-art compression efficiency in various tasks. We further make use of the hardware video encoding and decoding module available on GPUs to create a framework capable of both inference and training with video codecs repurposed as tensor codecs. This greatly reduces the requirement for memory capacity and communication bandwidth, enabling training and inference of large models on consumer-grade GPUs.