按年被提到
20232023 · 2 次2026
大模型与语言模型›混合专家与高效训练·arXiv:2306.00978 · cs.CL

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, Song Han · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-06-02 · 最近 2023-07-20
2不同的人
2活跃月份
2讨论串
284被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large language models (LLMs) have transformed numerous AI applications. On-device LLM is becoming increasingly important: running LLMs locally on edge devices can reduce the cloud computing cost and protect users' privacy. However, the astronomical model size and the limited hardware resource pose significant deployment challenges. We propose Activation-aware Weight Quantization (AWQ), a hardware-friendly approach for LLM low-bit weight-only quantization. AWQ finds that not all weights in an LLM are equally important. Protecting only 1% salient weights can greatly reduce quantization error. To identify salient weight channels, we should refer to the activation distribution, not weights. To avoid the hardware-inefficient mix-precision quantization, we mathematically derive that scaling up the salient channels can reduce the quantization error. AWQ employs an equivalent transformation to scale the salient weight channels to protect them. The scale is determined by collecting the activation statistics offline. AWQ does not rely on any backpropagation or reconstruction, so it generalizes to different domains and modalities without overfitting the calibration set. AWQ outperforms existing work on various language modeling and domain-specific benchmarks (coding and math). Thanks to better generalization, it achieves excellent quantization performance for instruction-tuned LMs and, for the first time, multi-modal LMs. Alongside AWQ, we implement TinyChat, an efficient and flexible inference framework tailored for 4-bit on-device LLM/VLMs. With kernel fusion and platform-aware weight packing, TinyChat offers more than 3x speedup over the Huggingface FP16 implementation on both desktop and mobile GPUs. It also democratizes the deployment of the 70B Llama-2 model on mobile GPUs.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论amanrs · 2023-07

“The key misconception about many quantization methods is that lower precision = better speed. I believe GPT-Q is not much faster than bf16 from skimming the AWQ paper - https://arxiv.org/pdf/2306.00978.pdf It's 3x faster for a batch size of 1, but that's still over 10x more expensive than gpt-3.5 For larger batch sizes, bf16 costs dip below 3-bit quant…”

Llama Is Expensive原评论 ↗
被提交为 story · 1 次