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/hxu160/CRCIR_for_PCGC
공식 코드Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinement
https://github.com/hyudsl/FDM
공식 코드Improving Detail in Pluralistic Image Inpainting with Feature Dequantization
https://github.com/hyx1999/quad
공식 코드QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition
https://github.com/iamcreateai/cyclevar
공식 코드CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation
https://github.com/iamkanghyunchoi/ait
공식 코드It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher
https://github.com/iamkanghyunchoi/qimera
공식 코드Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples
https://github.com/iankur/vqllm
공식 코드Residual vector quantization for KV cache compression in large language model
https://github.com/ibm/analog-foundation-models
공식 코드https://github.com/ibm/analog-nas
공식 코드AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory Computing
https://github.com/icey-zhang/ghost
공식 코드https://github.com/ichakra2/pca-hybrid
공식 코드https://github.com/ichbill/DQAS
공식 코드Dataset Quantization with Active Learning based Adaptive Sampling
https://github.com/ict-bigdatalab/clever
공식 코드Continual Learning for Generative Retrieval over Dynamic Corpora
https://github.com/ictnlp/sled-tts
공식 코드Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space
https://github.com/idea-emdoor-lab/distilcodec
공식 코드UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information
https://github.com/ielab/vec2text-dense_retriever-threat
공식 코드Understanding and Mitigating the Threat of Vec2Text to Dense Retrieval Systems
https://github.com/ifnspaml/Enhancement-Coded-Speech
공식 코드https://github.com/igorsokoloff/rr_with_compression_experiments_source_code
공식 코드Federated Optimization Algorithms with Random Reshuffling and Gradient Compression
https://github.com/ihounie/pd-qat
공식 코드https://github.com/iip-group/cs_regularizers
공식 코드https://github.com/ilkayw/cnn4fpga
공식 코드https://github.com/ilur98/dlmc-quant
공식 코드Towards Accurate Post-training Quantization for Reparameterized Models
https://github.com/imfinethanks/rep_adambnn
공식 코드RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via Repeating
https://github.com/imrl/gsb-vision-transformer
공식 코드GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples
https://github.com/in1k1/ce-vae-underwater-image-enhancement
공식 코드CE-VAE: Capsule Enhanced Variational AutoEncoder for Underwater Image Enhancement
https://github.com/index-tts/index-tts
공식 코드IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
https://github.com/inferflow/inferflow
공식 코드Inferflow: an Efficient and Highly Configurable Inference Engine for Large Language Models
https://github.com/insuhan/calibquant
공식 코드https://github.com/int-flashattention2024/int-flashattention
공식 코드INT-FlashAttention: Enabling Flash Attention for INT8 Quantization
https://github.com/intel-analytics/BigDL
공식 코드BigDL 2.0: Seamless Scaling of AI Pipelines from Laptops to Distributed Cluster
https://github.com/intel/auto-round
공식 코드Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs
https://github.com/intel/intel-extension-for-transformers
공식 코드https://github.com/intel/neural-compressor
공식 코드Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs
https://github.com/intellabs/fp8-emulation-toolkit
공식 코드https://github.com/intellabs/model-compression-research-package
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.