DUCKQUANT / THE QUANT & AI DIRECTORY
14,444 resources, ranked by in-directory PageRank
Showing 4,429–4,464 of 14,444 resources
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Accessible large language models via k-bit quantization for PyTorch.
The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models
This project is the official implementation of our accepted ICLR 2022 paper BiBERT: Accurate Fully Binarized BERT.
[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
Code repo for the paper BiT Robustly Binarized Multi-distilled Transformer
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
Reorder-based post-training quantization for large language model
Publication: Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model. Published Jun 3, 2019.
Publication: GOBO: Quantizing Attention-Based NLP Models for Low Latency and Energy Efficient Inference. Published May 8, 2020.
Publication: Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation. Published Nov 2020.
Publication: TernaryBERT: Distillation-aware Ultra-low Bit BERT. Published Sep 27, 2020.
Publication: KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization. Published Jan 15, 2021.
Publication: Understanding and Overcoming the Challenges of Efficient Transformer Quantization. Published Sep 27, 2021.
Publication: On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers. Published Aug 2021.
Publication: BinaryBERT: Pushing the Limit of BERT Quantization. Published Dec 31, 2020.
Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
[ICML'21 Oral] I-BERT: Integer-only BERT Quantization
Publication: PTQ4SAM: Post-Training Quantization for Segment Anything. Published 2024.
Publication: AQ-DETR: Low-Bit Quantized Detection Transformer with Auxiliary Queries. Published Mar 24, 2024.
Publication: Bi-ViT: Pushing the Limit of Vision Transformer Quantization. Published Mar 24, 2024.
Publication: Instance-Aware Group Quantization for Vision Transformers. Published 2024.
Explore this resource at its source website for documentation and current information.
Public repository by Qualcomm-AI-research. Primary language: Python.
Explore this resource at its source website for documentation and current information.
Explore this resource at its source website for documentation and current information.
Explore this resource at its source website for documentation and current information.
Explore this resource at its source website for documentation and current information.
Publication: FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer. Published Nov 27, 2021.
Publication: Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT Systems. Published Mar 22, 2023.
Publication: Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision. Published Jul 1, 2023.
Publication: PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers. Published Sep 13, 2022.
Explore this resource at its source website for documentation and current information.
