GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

作者： Elias Frantar, Saleh Ashkboos, Torsten Hoefler, Dan Alistarh (2022)

arXiv： 2210.17323

领域

推理

TLDR（中文）

第一次实现"在单卡上 4-bit 量化 175B 模型而几乎不掉精度"。把 LLM 推理硬件门槛从 8xA100 拉到一张消费级显卡，普及"开源大模型本地跑"。

TLDR (English)

First to achieve "4-bit quantization of 175B model on single GPU with almost no accuracy loss". Lowered LLM inference hardware barrier from 8xA100 to single consumer GPU, popularizing "run open-source LLMs locally".

出现在这些文章里

• KV Cache 与量化：让大模型跑得更快
• KV Cache and Quantization: Making Large Models Faster

同被引用

这些论文与本文出现在同一篇文章中

• LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale Tim Dettmers et al. (2022)
• QLoRA: Efficient Finetuning of Quantized LLMs Tim Dettmers et al. (2023)
• Efficient Memory Management for Large Language Model Serving with PagedAttention Woosuk Kwon et al. (2023)
• AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration Ji Lin et al. (2023)

相关论文

同一领域的其他论文

• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model DeepSeek-AI (2024)
  架构推理
• FlashAttention-3: Fast and Accurate Attention with Asympotic IO Complexity Jay Shah et al. (2024)
  推理
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters Charlie Snell et al. (2024)
  推理能力推理
• GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints Joshua Ainslie et al. (2023)
  推理架构
• Accelerating Large Language Model Decoding with Speculative Sampling Charlie Chen et al. (2023)
  推理
• FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning Tri Dao (2023)
  推理