3 citations · 6 across the 5 of their papers we have counts for
6 papers
Empowering Hybrid Attention Models on NPUs
Yinyuan Zhang, Daliang Xu, Xiaolong Huang +4
Hybrid attention models have emerged as a crucial architecture for Large Language Models (LLMs) (e.g., the Qwen3.5 and Kimi series). Their memory and computational efficiency make…
ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference
Wangsong Yin, Daliang Xu, Mengwei Xu +2
On-device running Large Language Models (LLMs) is nowadays a critical enabler towards preserving user privacy. We observe that the attention operator falls back from the special-pu…
Elastic On-Device LLM Service
Wangsong Yin, Rongjie Yi, Daliang Xu +3
On-device Large Language Models (LLMs) are transforming mobile AI, catalyzing applications like UI automation without privacy concerns. Nowadays the common practice is to deploy a…
Fast On-device LLM Inference with NPUs
Daliang Xu, Hao Zhang, Liming Yang +4
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…
Research on WebAssembly Runtimes: A Survey
Yixuan Zhang, Mugeng Liu, Haoyu Wang +3
WebAssembly (abbreviated as Wasm) was initially introduced for the Web but quickly extended its reach into various domains beyond the Web. To create Wasm applications, developers c…
Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading
Daliang Xu, Mengwei Xu, Qipeng Wang +6
This paper proposes Mandheling, the first system that enables highly resource-efficient on-device training by orchestrating the mixed-precision training with on-chip Digital Signal…