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/biomistral/biomistral
공식 코드BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains
https://github.com/biswajitsc/sparse-embed
공식 코드https://github.com/blauigris/jumpstart-cpaior
공식 코드Training Thinner and Deeper Neural Networks: Jumpstart Regularization
https://github.com/blueanon/bd-bnn
공식 코드https://github.com/bluorion-com/refine_massive_activations
공식 코드https://github.com/bluorion-com/weight_rescaling
공식 코드https://github.com/bo-liu-tum/encodingnet
공식 코드EncodingNet: A Novel Encoding-based MAC Design for Efficient Neural Network Acceleration
https://github.com/bollossom/qsd-transformer
공식 코드https://github.com/boluoweifenda/WAGE
공식 코드Training Quantized Deep Neural Networks via Cooperative Coevolution
https://github.com/borealisai/neuzip
공식 코드NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks
https://github.com/boschresearch/imax-calibration
공식 코드Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning
https://github.com/bowenl0218/mmvc_video_codec
공식 코드https://github.com/brave-experiments/melt-public
공식 코드https://github.com/brotherhappy/ostquant
공식 코드https://github.com/buaavrcg/LEGaussians
공식 코드Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding
https://github.com/burcgokden/Power-Law-Graph-Transformer
공식 코드Power Law Graph Transformer for Machine Translation and Representation Learning
https://github.com/bytedance/QSync
공식 코드QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices
https://github.com/bytedance/abq-llm
공식 코드ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models
https://github.com/bytedance/affinequant
공식 코드AffineQuant: Affine Transformation Quantization for Large Language Models
https://github.com/bytedance/decoupleq
공식 코드https://github.com/bytedance/mrecg
공식 코드Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
https://github.com/bytedance/qraf
공식 코드QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression
https://github.com/calad0i/HGQ
공식 코드Gradient-based Automatic Mixed Precision Quantization for Neural Networks On-Chip
https://github.com/calad0i/HGQ-demos
공식 코드Gradient-based Automatic Mixed Precision Quantization for Neural Networks On-Chip
https://github.com/calvintanama/qd-driver-activity-reco
공식 코드https://github.com/cambridge-mlg/combiner
공식 코드https://github.com/cambridge-mlg/miracle
공식 코드Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters
https://github.com/cambridge-mlg/recombiner
공식 코드RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations
https://github.com/cantbebetter2/mpq-dm
공식 코드MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models
https://github.com/carldesousatrias/findthelady
공식 코드Find the Lady: Permutation and Re-Synchronization of Deep Neural Networks
https://github.com/cat538/mxmoe
공식 코드MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design
https://github.com/cc-hpc-itwm/TensorQuant
공식 코드TensorQuant - A Simulation Toolbox for Deep Neural Network Quantization
https://github.com/cccrrrccc/fp4dit
공식 코드FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers
https://github.com/cfifty/rotation_trick
공식 코드https://github.com/cfm-uestc/DPQ
공식 코드Beyond Product Quantization: Deep Progressive Quantization for Image Retrieval
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.