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/namespace-pt/adon
공식 코드Hybrid Inverted Index Is a Robust Accelerator for Dense Retrieval
https://github.com/natasasdj/anomalyDetection
공식 코드Fast Distance-based Anomaly Detection in Images Using an Inception-like Autoencoder
https://github.com/naver-aics/lut-gemm
공식 코드https://github.com/naver/posegpt
공식 코드PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting
https://github.com/nbasyl/OFQ
공식 코드Oscillation-free Quantization for Low-bit Vision Transformers
https://github.com/nbasyl/llm-fp4
공식 코드https://github.com/necla-ml/diff-jpeg
공식 코드https://github.com/neonho/coarse-fine-weight-split
공식 코드Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting
https://github.com/neuralchecker/pyModelExtractor
공식 코드https://github.com/neuralchecker/pymodelextractor_towards_efficient_active_learning_of_PDFA_experiments
공식 코드https://github.com/neuralmagic/sparseml
공식 코드The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models
https://github.com/neuripss2020/kccotgan
공식 코드Conditional COT-GAN for Video Prediction with Kernel Smoothing
https://github.com/neurosim/DNN_NeuroSim_V2.0
공식 코드https://github.com/nexaai/awesome-llms-on-device
공식 코드https://github.com/nightmare-n/pvt-ssd
공식 코드PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer
https://github.com/nl2g/xcomet-lite
공식 코드xCOMET-lite: Bridging the Gap Between Efficiency and Quality in Learned MT Evaluation Metrics
https://github.com/nla-group/fabba
공식 코드https://github.com/nlescoua/faiss-quickeradc
공식 코드Quicker ADC : Unlocking the hidden potential of Product Quantization with SIMD
https://github.com/noakliu/efficient-foundation-models-survey
공식 코드Designing Large Foundation Models for Efficient Training and Inference: A Survey
https://github.com/noamelata/AdaSense
공식 코드https://github.com/nolanoorg/spectrasuite
공식 코드Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale
https://github.com/nthakur20/income
공식 코드https://github.com/nvidia/tensorrt-llm
공식 코드AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
https://github.com/nvlabs/coat
공식 코드COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
https://github.com/ondrejmokry/AudioRestorationFramework
공식 코드https://github.com/onnoo/activation-spikes
공식 코드Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs
https://github.com/opengvlab/efficientqat
공식 코드EfficientQAT: Efficient Quantization-Aware Training for Large Language Models
https://github.com/opengvlab/omniquant
공식 코드OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
https://github.com/openmotionlab/motiongpt
공식 코드https://github.com/openvinotoolkit/nncf
공식 코드Neural Network Compression Framework for fast model inference
https://github.com/openvinotoolkit/nncf_pytorch
공식 코드Neural Network Compression Framework for fast model inference
https://github.com/openvinotoolkit/openvino_notebooks
공식 코드Leveraging Speculative Sampling and KV-Cache Optimizations Together for Generative AI using OpenVINO
https://github.com/oravus/CoarseHash
공식 코드https://github.com/osu-srml/DP_Linprog
공식 코드Privacy-Aware Randomized Quantization via Linear Programming
https://github.com/otroshi/edgeface
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.