Quick Review: SmoothQuant: Accurate and Efficient Post-Training Quantization for LLMs| 东毅居士

Quick Review: SmoothQuant: Accurate and Efficient Post-Training Quantization for LLMs

作者：XD / 发表： 2023年12月7日 00:45 / 更新： 2023年12月7日 00:57 / 科研学习 / 阅读量：2396

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Paper: SmoothQuant on arXiv
Code: SmoothQuant on GitHub
Organization: MIT

Highlight:

Hyper-parameter for Outliers: Implements a novel approach using a specific hyper-parameter to manage outliers effectively during the quantization process.

本文作者：XD 转载请标明出处：http://www.eadst.com/blog/229

本站采用知识共享署名-非商业性使用-相同方式共享 4.0 国际许可协议进行许可。

上一篇
Quick Review: AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

下一篇
Setting Up v2rayNG with Tencent Cloud Silicon Valley Lighthouse

Category

标签云

News WAN CSV GPTQ Paddle FP16 Hilton TensorRT Domain Sklearn Crawler Zip 图标 Math Paper torchinfo uwsgi NameSilo Vim LLM Diagram Food 阿里云腾讯云 Qwen2 ONNX Linux SQL 第一性原理 Random LeetCode Git FP64 Excel printf diffusers 算法题 XGBoost GIT GPT4 ms-swift Color Logo scipy BeautifulSoup Streamlit Github Safetensors CEIR 图形思考法 DeepStream Review GGML Image2Text Google Land Ptyhon GoogLeNet LLAMA Mixtral PIP 云服务器 Proxy hf 飞书 Qwen PDF Michelin Input Qwen2.5 C++ Distillation Jetson Website Django Hungarian 继承净利润 Tensor RL Password API mmap 签证 UI Nginx SQLite 顶会 Python SAM SVR OCR Jev icon Knowledge Freesound 递归学习法 Permission JSON CLAP 版权 Bitcoin Bipartite API网关 Transformers Anaconda DeepSeek Clash Interview git ResNet-50 Baidu LaTeX Pickle AI Miniforge logger 搞笑 Datetime SPIE v0.dev CC MD5 Quantize FP8 Numpy Web Windows 多线程 Claude Pillow XML Tracking Cloudreve 公式 CTC uWSGI Magnet BTC Augmentation 论文速读多进程 Animate Base64 Firewall Bert 财报 COCO CAM ModelScope Heatmap Use Template tqdm transformers OpenAI Plate Search Card QWEN tar PyCharm RGB Gemma Pytorch git-lfs PDB Quantization RAR VPN NLTK TTS Ubuntu TSV Algorithm FastAPI InvalidArgumentError PyTorch VSCode Harness Conda CUDA HaggingFace 强化学习 VGG-16 OpenCV Tiktoken WebCrawler Data YOLO Shortcut ChatGPT Llama FlashAttention UNIX Jupyter llama.cpp 报税 EXCEL LoRA Markdown Hotel Translation Bin CV Disk Breakpoint Attention Agent 关于博主 Docker TensorFlow Plotly Statistics HuggingFace Dataset Rebuttal Video NLP 域名 Pandas BF16 论文 v2ray Vmess 音频 FP32 证件照 IndexTTS2

站点统计

本站现有博文337篇,共被浏览961508次

本站已经建立2673天!

原 Quick Review: SmoothQuant: Accurate and Efficient Post-Training Quantization for LLMs

作者：XD / 发表： 2023年12月7日 00:45 / 更新： 2023年12月7日 00:57 / 科研学习 / 阅读量：2396

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Highlight:

Quick Review: SmoothQuant: Accurate and Efficient Post-Training Quantization for LLMs