thu-nics / FrameFusion
The official code implementation of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"
☆24Updated this week
Alternatives and similar repositories for FrameFusion:
Users that are interested in FrameFusion are comparing it to the libraries listed below
- Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference" proposed by Pekin…☆71Updated 3 months ago
- This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality"☆45Updated 2 weeks ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆41Updated this week
- Accelerating Diffusion Transformers with Token-wise Feature Caching☆49Updated this week
- The code repository of "MBQ: Modality-Balanced Quantization for Large Vision-Language Models"☆28Updated last month
- ☆131Updated 2 weeks ago
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆92Updated 6 months ago
- [NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.☆60Updated 3 weeks ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆45Updated last month
- Code release for VTW (AAAI 2025) Oral☆30Updated last week
- 📚 Collection of awesome generation acceleration resources.☆112Updated this week
- [ICLR 2024 Spotlight] This is the official PyTorch implementation of "EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Di…☆55Updated 7 months ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆113Updated 8 months ago
- [CVPR 2024 Highlight] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Mo…☆60Updated 5 months ago
- [ICLR 2025] MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More☆28Updated last week
- This is the official pytorch implementation for the paper: Towards Accurate Post-training Quantization for Diffusion Models.(CVPR24 Poste…☆34Updated 7 months ago
- Curated list of methods that focuses on improving the efficiency of diffusion models☆35Updated 6 months ago
- QuEST: Efficient Finetuning for Low-bit Diffusion Models☆36Updated last week
- [NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification☆17Updated 5 months ago
- PyTorch code for Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers☆36Updated 4 months ago
- ☆47Updated last week
- PyTorch implementation of PTQ4DiT https://arxiv.org/abs/2405.16005☆19Updated 2 months ago
- The official code of the paper "PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction".☆51Updated 3 weeks ago
- [EMNLP 2024 Findings🔥] Official implementation of "LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Infe…☆89Updated 2 months ago
- DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆20Updated 3 weeks ago
- [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation☆212Updated last week
- PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models☆24Updated last month
- ☆12Updated this week
- torch_quantizer is a out-of-box quantization tool for PyTorch models on CUDA backend, specially optimized for Diffusion Models.☆21Updated 10 months ago
- The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"☆40Updated last month