Alternatives and similar repositories for ZipCache

Users that are interested in ZipCache are comparing it to the libraries listed below

• ThisisBillhe / ZipAR
  This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality"
  ☆47Updated last month
• thu-nics / FrameFusion
  The official code implementation of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"
  ☆39Updated last month
• thu-nics / MBQ
  The code repository of "MBQ: Modality-Balanced Quantization for Large Vision-Language Models"
  ☆38Updated last month
• mit-han-lab / x-attention
  XAttention: Block Sparse Attention with Antidiagonal Scoring
  ☆146Updated last month
• xuyang-liu16 / Awesome-Token-level-Model-Compression
  📚 Collection of token reduction for model compression resources.
  ☆53Updated 2 weeks ago
• thu-nics / ViDiT-Q
  [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
  ☆92Updated last month
• Hsu1023 / DuQuant
  [NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.
  ☆159Updated 7 months ago
• Juanerx / Q-DiT
  [CVPR 2025] Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
  ☆48Updated 8 months ago
• Aaronhuang-778 / Mixture-Compressor-MoE
  [ICLR 2025] Mixture Compressor for Mixture-of-Experts LLMs Gains More
  ☆43Updated 3 months ago
• lzhxmu / VTW
  Code release for VTW (AAAI 2025) Oral
  ☆39Updated 3 months ago
• thu-nics / DiTFastAttn
  ☆164Updated 4 months ago
• JinXins / Awesome-Token-Merge-for-MLLMs
  A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.
  ☆54Updated 4 months ago
• SUSTechBruce / LOOK-M
  [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…
  ☆93Updated 6 months ago
• ChangyuanWang17 / QVLM
  [NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.
  ☆73Updated 4 months ago
• cat538 / SKVQ
  SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models
  ☆19Updated 7 months ago
• Theia-4869 / FasterVLM
  Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.
  ☆74Updated 5 months ago
• Gumpest / SparseVLMs
  [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".
  ☆102Updated last week
• KD-TAO / DyCoke
  DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
  ☆43Updated last month
• mdy666 / Qwen-Native-Sparse-Attention
  qwen-nsa
  ☆60Updated last month
• horseee / learning-to-cache
  [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
  ☆102Updated 9 months ago
• AkideLiu / MiniCache
  ☆9Updated 8 months ago
• LINs-lab / DynMoE
  [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models
  ☆89Updated 3 months ago
• Intelligent-Computing-Lab-Yale / GPTQv2
  Code implementation of GPTQv2 (https://arxiv.org/abs/2504.02692)
  ☆36Updated 3 weeks ago
• ModelTC / TFMQ-DM
  [CVPR 2024 Highlight] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Mo…
  ☆63Updated 9 months ago
• mit-han-lab / Block-Sparse-Attention
  A sparse attention kernel supporting mix sparse patterns
  ☆202Updated 3 months ago
• prathebaselva / FORA
  FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.
  ☆45Updated 10 months ago
• VainF / MaskLLM-4V
  Learnable Semi-structured Sparsity for Vision Transformers and Diffusion Transformers
  ☆11Updated 3 months ago
• zhijie-group / Orthus
  ☆29Updated 3 weeks ago
• hahnyuan / ASVD4LLM
  Activation-aware Singular Value Decomposition for Compressing Large Language Models
  ☆66Updated 6 months ago
• ThisisBillhe / torch_quantizer
  torch_quantizer is a out-of-box quantization tool for PyTorch models on CUDA backend, specially optimized for Diffusion Models.
  ☆22Updated last year