https://github.com/xiaocaigou/qbaraqahira
공식 코드Accurate and Efficient Fine-Tuning of Quantized Large Language Models Through Optimal Balance
Papers with Code 아카이브
Quantization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 10
- 보존된 평가 기록
- 32
Quantization is a promising technique to reduce the computation cost of neural network training, which can replace high-cost floating-point numbers (e.g., float32) with low-cost fixed-point numbers (e.g., int8/int16).
Source: Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/xiaosu-zhu/McQuic
공식 코드Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
https://github.com/xinghaochen/tinysam
공식 코드TinySAM: Pushing the Envelope for Efficient Segment Anything Model
https://github.com/xinghaow99/bitstack
공식 코드BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
https://github.com/xingyu-zheng/bidm
공식 코드BiDM: Pushing the Limit of Quantization for Diffusion Models
https://github.com/xingyu-zheng/binarydm
공식 코드BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models
https://github.com/xinjie-q/gaussianimage
공식 코드GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting
https://github.com/xinyandai/product-quantization
공식 코드Norm-Explicit Quantization: Improving Vector Quantization for Maximum Inner Product Search
https://github.com/xinyue-li3/hybrid-lifting-structure
공식 코드https://github.com/xiyuanzh/awesome-llm-time-series
공식 코드https://github.com/xjjxmu/qslaw
공식 코드https://github.com/xl1990/astra
공식 코드Communication-Efficient Multi-Device Inference Acceleration for Transformer Models
https://github.com/xrenaa/Retriever
공식 코드Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph
https://github.com/xuke225/eq-net
공식 코드https://github.com/xushoukai/GDFQ
공식 코드https://github.com/xuyuzhuang11/onebit
공식 코드https://github.com/xvyaward/owq
공식 코드https://github.com/xvyaward/qeft
공식 코드https://github.com/yangfan-hu/fast-snn
공식 코드Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN
https://github.com/yanghr/BSQ
공식 코드BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization
https://github.com/yangling0818/vqgraph
공식 코드VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
https://github.com/yangyifei729/laco
공식 코드https://github.com/yanivbl6/quantized_meanfield
공식 코드A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off
https://github.com/yanjingli0202/q-vit
공식 코드Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer
https://github.com/yanyang19/ImPart
공식 코드ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs
https://github.com/yaomingshuai/vq-font
공식 코드VQ-Font: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization
https://github.com/yc2367/bbs-micro
공식 코드BBS: Bi-directional Bit-level Sparsity for Deep Learning Acceleration
https://github.com/yc2367/bitmod-hpca-25
공식 코드https://github.com/ydyhello/tailorkv
공식 코드TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization
https://github.com/yeaso/Expansion-Quantization-Network-EQN
공식 코드Expansion Quantization Network: An Efficient Micro-emotion Annotation and Detection Framework
https://github.com/yhhhli/APoT_Quantization
공식 코드Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks
https://github.com/yhhhli/BRECQ
공식 코드BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
https://github.com/yihangchen-ee/hac
공식 코드HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression
https://github.com/yihangchen-ee/hac-plus
공식 코드https://github.com/yihangchen-ee/pcgs
공식 코드https://github.com/yikaiw/RS-Nets
공식 코드Resolution Switchable Networks for Runtime Efficient Image Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.