Kang Zhao

BoundaryDPT: Pushing the Boundaries of Depth Pruning for Vision Transformers

FlatQuant: Flatness Matters for LLM Quantization

A Simple Linear Patch Revives Layer-Pruned Large Language Models

Beyond 2:4: Exploring V:N:M Sparsity for Efficient Transformer Inference on GPUs

FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs for Efficient Inference

1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bit

FlatQuant: Flatness Matters for LLM Quantization

Zero-shot Quantization for Object Detection