AIJul 8, 2024

Fast On-device LLM Inference with NPUs

arXiv:2407.05858v273 citationsh-index: 49
Originality Incremental advance
AI Analysis

This addresses the problem of slow on-device LLM inference for mobile applications, offering significant performance improvements, though it is incremental in optimizing existing hardware usage.

The paper tackles high inference latency in on-device LLMs, particularly during the prefill stage, by introducing llm.npu, a system that uses NPU offloading with multi-level optimizations, achieving up to 32.8x speedup and over 1,000 tokens/sec for billion-sized models.

On-device inference for Large Language Models (LLMs), driven by increasing privacy concerns and advancements of mobile-sized models, has gained significant interest. However, even mobile-sized LLMs (e.g., Gemma-2B) encounter unacceptably high inference latency, often bottlenecked by the prefill stage in tasks like screen UI understanding. We present llm.npu, the first LLM inference system utilizing on-device Neural Processing Unit (NPU) offloading to reduce prefill latency. llm.npu enhances NPU offloading efficiency by re-constructing the prompt and model in three levels: (1) At prompt level, it divides variable-length prompts into multiple fixed-sized chunks while maintaining data dependencies; (2) At tensor level, it identifies and extracts significant outliers to run on the CPU/GPU in parallel with minimal overhead; (3) At block level, it schedules Transformer blocks in an out-of-order manner to the CPU/GPU and NPU based on their hardware affinity and sensitivity to accuracy. Compared to competitive baselines, llm.npu achieves 22.4x faster prefill speed and 30.7$\times$ energy savings on average, and up to 32.8x speedup in an end-to-end real-world application. For the first time, llm.npu achieves more than 1,000 tokens/sec prefilling for a billion-sized model.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes