ODMA: On-Demand Memory Allocation Framework for LLM Serving on LPDDR-Class Accelerators

Serving large language models (LLMs) on accelerators with poor random-access bandwidth (e.g., LPDDR5-based) is limited by current memory managers. Static pre-allocation wastes memory, while fine-grained paging (e.g., PagedAttention) is ill-suited due to high random-access costs. Existing HBM-centric solutions do not exploit the characteristics of random-access-constrained memory (RACM) accelerators like Cambricon MLU370. We present ODMA, an on-demand memory allocation framework for RACM. ODMA addresses distribution drift and heavy-tailed requests by coupling a lightweight length predictor with dynamic bucket partitioning and a large-bucket safeguard. Boundaries are periodically updated from live traces to maximize utilization. On Alpaca and Google-NQ, ODMA improves prediction accuracy of prior work significantly (e.g., from 82.68% to 93.36%). Serving DeepSeek-R1-Distill-Qwen-7B on Cambricon MLU370-X4, ODMA raises memory utilization from 55.05% to 72.45% and improves RPS and TPS by 29% and 27% over static baselines. This demonstrates that hardware-aware allocation unlocks efficient LLM serving on RACM platforms.