ThisisBillhe / ZipCache
[NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
☆18Updated 7 months ago
Alternatives and similar repositories for ZipCache:
Users that are interested in ZipCache are comparing it to the libraries listed below
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆59Updated 2 weeks ago
- [NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.☆144Updated 5 months ago
- This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality"☆46Updated last month
- The code repository of "MBQ: Modality-Balanced Quantization for Large Vision-Language Models"☆33Updated this week
- [ICML'24 Oral] APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference☆33Updated 9 months ago
- The official code implementation of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"☆33Updated 3 weeks ago
- [ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Mod…☆35Updated last year
- [NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.☆67Updated 2 months ago
- ☆149Updated last month
- 📚 Collection of token reduction for model compression resources.☆44Updated 3 weeks ago
- [CVPR 2025] Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers☆38Updated 6 months ago
- [EMNLP 2024 Findings🔥] Official implementation of ": D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Larg…☆92Updated 4 months ago
- [ICLR 2024 Spotlight] This is the official PyTorch implementation of "EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Di…☆58Updated 9 months ago
- torch_quantizer is a out-of-box quantization tool for PyTorch models on CUDA backend, specially optimized for Diffusion Models.