Ryuto Tanigawa

Sensitivity-Guided Mixed-Precision Post-Training Quantization for MambaVision

Hybrid vision backbones such as MambaVision combine convolutional layers, Mamba blocks (based on selective state space models), and self-attention within a single architecture. However, the heterogeneous operator composition of such models poses new challenges for post-training quantization (PTQ): uniform bit-width ass...