THU-MIG / PrefixKVLinks
PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation [NeurIPS 2025]
☆13Updated last week
Alternatives and similar repositories for PrefixKV
Users that are interested in PrefixKV are comparing it to the libraries listed below
Sorting:
- Code release for VTW (AAAI 2025 Oral)☆50Updated 3 months ago
- [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Cont…☆56Updated last month
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆74Updated 9 months ago
- Cross-Self KV Cache Pruning for Efficient Vision-Language Inference☆10Updated 10 months ago
- A generalized framework for subspace tuning methods in parameter efficient fine-tuning.☆154Updated 3 months ago
- The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"☆48Updated 9 months ago
- ☆58Updated 5 months ago
- [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…☆103Updated 11 months ago
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models☆135Updated 3 months ago
- [ICML 2023] UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers☆105Updated 9 months ago
- [NeurIPS2023] Parameter-efficient Tuning of Large-scale Multimodal Foundation Model☆88Updated last year
- Official code for our paper, "LoRA-Pro: Are Low-Rank Adapters Properly Optimized? "☆132Updated 6 months ago
- D^2-MoE: Delta Decompression for MoE-based LLMs Compression☆68Updated 6 months ago
- ☆119Updated last year
- CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for task-aware parameter-efficient fine-tuning(NeurIPS 2024)☆52Updated 9 months ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆150Updated 3 weeks ago
- [ICLR 2025] Official implementation of paper "Dynamic Low-Rank Sparse Adaptation for Large Language Models".☆23Updated 7 months ago
- [ICML'24 Oral] APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference☆45Updated last year
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆93Updated 3 months ago
- [ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"☆63Updated 2 weeks ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆35Updated 9 months ago
- ICLR 2024, Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching☆101Updated last year
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆171Updated 4 months ago
- Official Pytorch Implementation of "Outlier-weighed Layerwise Sampling for LLM Fine-tuning" by Pengxiang Li, Lu Yin, Xiaowei Gao, Shiwei …☆34Updated 4 months ago
- Efficient Mixture of Experts for LLM Paper List☆136Updated 3 weeks ago
- [AAAI 2024] Fluctuation-based Adaptive Structured Pruning for Large Language Models☆61Updated last year
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆79Updated 3 weeks ago
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆66Updated 6 months ago
- Code for "ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models" (ICLR 2024)☆20Updated last year
- Pruning the VLLMs☆103Updated 10 months ago