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

作者： Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, Song Han (2022)

arXiv： 2211.10438

领域

推理

TLDR（中文）

把激活的 outlier 通过等价数学变换"挪"到权重上，使得 INT8 推理可行。是 GPU FP8/INT8 部署能 work 的关键工程发现。

TLDR (English)

Moves activation outliers to weights through equivalent mathematical transformation, making INT8 inference feasible. Key engineering discovery enabling GPU FP8/INT8 deployment.

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)
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers Elias Frantar et al. (2022)
• Efficient Memory Management for Large Language Model Serving with PagedAttention Woosuk Kwon 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