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：2435

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

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

站点统计

本站现有博文338篇,共被浏览976428次

本站已经建立2689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：2435

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

Highlight:

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