DUCKQUANT / THE QUANT & AI DIRECTORY
14,444 resources, ranked by in-directory PageRank
Showing 4,357–4,392 of 14,444 resources
Publication: A Survey of Quantization Methods for Efficient Neural Network Inference. Published Mar 25, 2021.
zkkli has 7 repositories available. Follow their code on GitHub.
Publication: Accurate LoRA-Finetuning Quantization of LLMs via Information Retention. Published Feb 8, 2024.
Publication: RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization. Published Feb 8, 2024.
Publication: Squat: Quant Small Language Models on the Edge. Published Feb 16, 2024.
Publication: APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models. Published Feb 21, 2024.
Publication: GPTVQ: The Blessing of Dimensionality for LLM Quantization. Published Feb 23, 2024.
Publication: A Comprehensive Evaluation of Quantization Strategies for Large Language Models. Published Feb 26, 2024.
Publication: FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization. Published Feb 28, 2024.
Publication: IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact. Published Mar 2, 2024.
Publication: EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs. Published Mar 5, 2024.
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.
Explore this resource at its source website for documentation and current information.
Publication: What Makes Quantization for Large Language Model Hard? An Empirical Study from the Lens of Perturbation. Published Mar 24, 2024.
Publication: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation. Published Mar 24, 2024.
Publication: Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge. Published Mar 24, 2024.
Publication: Norm Tweaking: High-Performance Low-Bit Quantization of Large Language Models. Published Mar 24, 2024.
Publication: OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models. Published Mar 24, 2024.
Publication: ZeroQuant-HERO: Hardware-Enhanced Robust Optimized Post-Training Quantization Framework for W8A8 Transformers. Published Oct 26, 2023.
Publication: Atom: Low-bit Quantization for Efficient and Accurate LLM Serving. Published Oct 29, 2023.
Publication: QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models. Published Oct 25, 2023.
Publication: QFT: Quantized Full-parameter Tuning of LLMs with Affordable Resources. Published Oct 11, 2023.
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: Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization. Published Nov 28, 2023.
Publication: AFPQ: Asymmetric Floating Point Quantization for LLMs. Published Nov 3, 2023.
Publication: A Speed Odyssey for Deployable Quantization of LLMs. Published Nov 16, 2023.
Publication: SmoothQuant+: Accurate and Efficient 4-bit Post-Training WeightQuantization for LLM. Published Dec 6, 2023.
Publication: Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge. Published Dec 9, 2023.
Publication: FP8-BERT: Post-Training Quantization for Transformer. Published Dec 10, 2023.
Publication: CBQ: Cross-Block Quantization for Large Language Models. Published Dec 13, 2023.
Publication: ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks. Published Dec 14, 2023.
