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/squeezeailab/kvquant
공식 코드KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
https://github.com/squeezeailab/squeezellm
공식 코드https://github.com/squeezeailab/tinyagent
공식 코드https://github.com/squeezebits/quick
공식 코드QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
https://github.com/st4cks1defl0w/hcvq
공식 코드Homology-constrained vector quantization entropy regularizer
https://github.com/stanis-morozov/unq
공식 코드Unsupervised Neural Quantization for Compressed-Domain Similarity Search
https://github.com/stanleybak/quantized_nn_backreach
공식 코드https://github.com/staoxiao/libvq
공식 코드https://github.com/starxliu/FDDH
공식 코드FDDH: Fast Discriminative Discrete Hashing for Large-Scale Cross-Modal Retrieval
https://github.com/stevetsui/q-detr
공식 코드Q-DETR: An Efficient Low-Bit Quantized Detection Transformer
https://github.com/stiphyjay/lidar-ptq
공식 코드LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection
https://github.com/stochasticai/xturing
공식 코드https://github.com/stockeh/canine-embedded-ml
공식 코드Who's a Good Boy? Reinforcing Canine Behavior in Real-Time using Machine Learning
https://github.com/suakaw/bdq_privacyar
공식 코드Privacy-Preserving Action Recognition via Motion Difference Quantization
https://github.com/subiawaud/PWFN
공식 코드https://github.com/submission2019/cnn-quantization
공식 코드Post-training 4-bit quantization of convolution networks for rapid-deployment
https://github.com/sunblaze-ucb/llm-api-audit
공식 코드Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
https://github.com/sungonuni/HOT
공식 코드https://github.com/supercomputing-system-ai-lab/milo
공식 코드MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators
https://github.com/surajkra/Offside_Tracker_EECS504
공식 코드https://github.com/swing-research/opu_phase
공식 코드Don't take it lightly: Phasing optical random projections with unknown operators
https://github.com/sylvaincom/astride
공식 코드https://github.com/synsense/rockpool
공식 코드Gradient-descent hardware-aware training and deployment for mixed-signal Neuromorphic processors
https://github.com/tabrizian/learning-to-quantize
공식 코드https://github.com/taeheej/4bit-quantization-in-vector-embedding-for-rag
공식 코드https://github.com/tajanthan/pmf
공식 코드https://github.com/talkking/MixGPT
공식 코드One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models
https://github.com/talwagner/lsq
공식 코드Fast Private Kernel Density Estimation via Locality Sensitive Quantization
https://github.com/tamasham/napa-vq
공식 코드NAPA-VQ: Neighborhood Aware Prototype Augmentation with Vector Quantization for Continual Learning
https://github.com/taufeeque9/codebook-features
공식 코드Codebook Features: Sparse and Discrete Interpretability for Neural Networks
https://github.com/taylorjocelyn/d2-dpm
공식 코드D$^2$-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models
https://github.com/taylorjocelyn/diffusion-model-quantization
공식 코드https://github.com/tbijl/course_ranking_data
공식 코드Efficient course recommendations with T5-based ranking and summarization
https://github.com/techmonsterwang/illama
공식 코드https://github.com/technicolor-research/faiss-quickeradc
공식 코드Quicker ADC : Unlocking the hidden potential of Product Quantization with SIMD
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.