FAMPWQ: Fisher Information-based Adaptive Mixed Precision Weight Quantization for Effective LLM Inference
A novel Fisher information-based Adaptive Mixed Precision Weight Quantization approach, i.e., FAMPWQ, which performs layer-adaptive weight quantization for effective LLM inference on commodity GPUs and a reinforcement learning-based bit-width allocator in FAMPWQ, which generates an adaptive bit-width allocation strateg...
G. Lee, Ji Liu, Jun-Cheng Jia et al.
· 0 citations