Accelerating OpenPangu Inference on NPU via Speculative Decoding
Yuntao Dai, Jing Wu, Hang Gu, Teng Wang

TL;DR
This paper proposes a speculative decoding acceleration scheme for OpenPangu-7B to improve inference speed on NPU hardware, addressing memory bottlenecks and lack of native support for such algorithms.
Contribution
It introduces an end-to-end speculative inference acceleration method tailored for OpenPangu-7B on NPU hardware, overcoming existing hardware limitations.
Findings
Significant speedup in inference time on NPU hardware
Effective mitigation of memory wall bottleneck
Compatibility with mainstream speculative decoding algorithms
Abstract
To mitigate the Memory Wall bottleneck encountered by Large Language Models (LLMs) during inference on \textbf{NPU} hardware, and addressing the scarcity of native support for mainstream speculative decoding algorithms on domestic infrastructure, this study presents an end-to-end speculative inference acceleration scheme for OpenPangu-7B.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning and Algorithms · Generative Adversarial Networks and Image Synthesis · Natural Language Processing Techniques
