QuantaSpike: Short-Window Spike-Driven Quantization for Large Language Models
QuantaSpike is proposed, a short-window spike-driven quantization framework for LLMs built around Logarithmic Ternary Integrate-and-Fire (LTIF) neurons that achieves state-of-the-art or competitive perplexity and zero-shot accuracy among spike-driven LLM quantization methods.
Bang Hu, Guo-Wei Zhu, Changze Lv et al.
· 0 citations