A powerful toolkit for compressing large models including LLM, VLM, and video generation models.

📚 Collection of token-level model compression resources.

This is a collection of our research on efficient AI, covering hardware-aware NAS and model compression.

Official implementation of CVPR 2024 paper "vid-TLDR: Training Free Token merging for Light-weight Video Transformer".

[CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models

HoliTom: Holistic Token Merging for Fast Video Large Language Models

A token pruning method that accelerates ViTs for various tasks while maintaining high performance.

Official Implementation (Pytorch) of the "Representation Shift: Unifying Token Compression with FlashAttention", ICCV 2025

An implementation of LazyLLM token pruning for LLaMa 2 model family.

Implementation of ICCV 2025 paper "Growing a Twig to Accelerate Large Vision-Language Models".

😎 Awesome papers on token redundancy reduction

Task-Specific Dynamic Token Pruning (TS-DTP) for LLMs