BitNet a4.8: 4-bit Activations for 1-bit LLMs
This work addresses efficiency in large-scale LLM deployment for AI practitioners, representing an incremental improvement over prior 1-bit models.
The paper tackles the problem of reducing inference cost in 1-bit LLMs by introducing BitNet a4.8, which uses 4-bit activations and achieves performance comparable to BitNet b1.58 with faster inference, activating only 55% of parameters and supporting a 3-bit KV cache.
Recent research on the 1-bit Large Language Models (LLMs), such as BitNet b1.58, presents a promising direction for reducing the inference cost of LLMs while maintaining their performance. In this work, we introduce BitNet a4.8, enabling 4-bit activations for 1-bit LLMs. BitNet a4.8 employs a hybrid quantization and sparsification strategy to mitigate the quantization errors introduced by the outlier channels. Specifically, we utilize 4-bit activations for inputs to the attention and feed-forward network layers, while sparsifying intermediate states followed with 8-bit quantization. Extensive experiments demonstrate that BitNet a4.8 achieves performance comparable to BitNet b1.58 with equivalent training costs, while being faster in inference with enabling 4-bit (INT4/FP4) kernels. Additionally, BitNet a4.8 activates only 55% of parameters and supports 3-bit KV cache, further enhancing the efficiency of large-scale LLM deployment and inference.