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/intelligent-computing-lab-yale/gptaq
공식 코드GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration
https://github.com/intelligent-computing-lab-yale/gptqv2
공식 코드GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration
https://github.com/intelligent-computing-lab-yale/mint-quantization
공식 코드MINT: Multiplier-less INTeger Quantization for Energy Efficient Spiking Neural Networks
https://github.com/intelligent-microsystems-lab/snnquantprune
공식 코드The Hardware Impact of Quantization and Pruning for Weights in Spiking Neural Networks
https://github.com/internlm/lmdeploy
공식 코드AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
https://github.com/ispamm/q-gesco
공식 코드Lightweight Diffusion Models for Resource-Constrained Semantic Communication
https://github.com/ist-daslab/cram
공식 코드https://github.com/ist-daslab/evopress
공식 코드EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search
https://github.com/ist-daslab/gptq
공식 코드GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/ist-daslab/halo
공식 코드HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs
https://github.com/ist-daslab/marlin
공식 코드MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models
https://github.com/ist-daslab/obc
공식 코드Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning
https://github.com/ist-daslab/quik
공식 코드QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models
https://github.com/ist-daslab/rosa
공식 코드RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation
https://github.com/ist-daslab/sparse-marlin
공식 코드MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models
https://github.com/ist-daslab/sparsefinetuning
공식 코드Sparse Fine-tuning for Inference Acceleration of Large Language Models
https://github.com/ist-daslab/sparsegpt
공식 코드SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
https://github.com/it-coimbra/redbit
공식 코드RedBit: An End-to-End Flexible Framework for Evaluating the Accuracy of Quantized CNNs
https://github.com/itayhubara/CalibTIP
공식 코드Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming
https://github.com/ituvisionlab/factorqvae
공식 코드Disentanglement with Factor Quantized Variational Autoencoders
https://github.com/iwhwang/Fine-Grained-Causal-RL
공식 코드https://github.com/jLooo/VADMamba
공식 코드VADMamba: Exploring State Space Models for Fast Video Anomaly Detection
https://github.com/jaewoosong/pocketnn
공식 코드https://github.com/jamestuna/clado_mpq
공식 코드Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic Programming
https://github.com/janenie/espn-nba-data
공식 코드Operations Guided Neural Networks for High Fidelity Data-To-Text Generation
https://github.com/jayLEE0301/vq_bet_official
공식 코드https://github.com/jayzhang0727/Faster-Binary-Embeddings-for-Preserving-Euclidean-Distances
공식 코드https://github.com/jdcomsearch/poeem
공식 코드Joint Learning of Deep Retrieval Model and Product Quantization based Embedding Index
https://github.com/jeeseung-park/viplo
공식 코드https://github.com/jerry-chee/discquant
공식 코드DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory
https://github.com/jerryxu0129/hhf
공식 코드HHF: Hashing-guided Hinge Function for Deep Hashing Retrieval
https://github.com/jeshraghian/snn-tha
공식 코드The fine line between dead neurons and sparsity in binarized spiking neural networks
https://github.com/jeshraghian/snntorch
공식 코드SQUAT: Stateful Quantization-Aware Training in Recurrent Spiking Neural Networks
https://github.com/jetrunner/beyond-preserved-accuracy
공식 코드Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression
https://github.com/jiaangl/randomquantization
공식 코드Random Entity Quantization for Parameter-Efficient Compositional Knowledge Graph Representation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.