Kevin Xu, Tatsuya Kubo, Daichi Tokuda, Shinya Takamaeda-Yamazaki, Issei Sato
原文摘要
Autoregressive decoding of large language models (LLMs) on edge devices is dominated by memory-bound general matrix--vector multiplication (GeMV) operations. Processing-using-DRAM (PUD) is a promising computing paradigm that can alleviate this bottleneck by reducing processor--memory data transfers and enabling massively parallel computation within DRAM (e.g., across 65,536 columns). However, weight matrices in individual LLM layers (e.g., a QKV matrix in Llama3 8B with 6,144 rows) are typically too small to fully utilize parallelism in PUD. To address this challenge, we propose an algorithm--system co-design for PUD-based LLM inference. At the algorithm level, we enable a subsequent projection to be packed with the current projection by reformulating it as a computation on the current residual state plus a correction for the residual update. Layer redundancy allows this correction to be approximated using fewer bit-serial steps. At the system level, we tailor data mapping and execution to improve utilization of either columns within DRAM subarrays (SIMD) or independently controlled banks (MIMD). Overall, we achieves up to $1.41\times$ end-to-end decoding speedup over the PUD baseline, corresponding to a $2.45\times$ speedup over processor-based execution.
Direct Preference Optimization (DPO) has been widely adopted for aligning language models with human preferences. Recent empirical work has revealed that DPO induces remarkably sparse parameter updates, yet no theoretical explanation for this phenomenon has been offered. We analyze DPO's optimization dynamics under a neural tangent kernel linearization and show that the logistic structure of the DPO loss gives rise to an implicit maximum-margin bias. Building on this observation, we introduce the concept of dual sparsity: the DPO update direction is a sparse linear combination (data-level sparsity, driven by support vectors) of sparse gradient feature vectors (parameter-level sparsity, arising from gradient cancellation between preferred and dispreferred responses). We formalize this structure in our main theorem, bound the number of support pairs by a margin-dependent spectral quantity, and present a framework relating dual sparsity to weight disentanglement---a condition favorable for model merging. Experiments on GPT-2 Small and Medium and on 7--9B instruction-tuned models (Llama-3-8B, Mistral-7B, Gemma-2-9B) with the Anthropic HH-RLHF and UltraFeedback datasets confirm both sources of sparsity, and experiments on GPT-2 show that DPO reduces cross-task interference by up to $35{\times}$ compared to supervised fine-tuning.