4 papers
UnionSparse: An Index-Efficient Sparsity Framework for Low-Bit Sparse LLM Inference on Edge
Tianhao Jiang, Hang Gu, Teng Wang +9
Edge LLM inference combines sparsity and low-bit quantization to meet device memory, latency, and power limits. Yet quantization shrinks weight payloads without proportionally redu…
Accelerating OpenPangu Inference on NPU via Speculative Decoding
Yuntao Dai, Jing Wu, Hang Gu +1
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 main…
Hermes: A Unified High-Performance NTT Architecture with Hybrid Dataflow
Hang Gu, Teng Wang, Qianyu Cheng +6
Fully Homomorphic Encryption (FHE) relies heavily on the Number Theoretic Transform (NTT), making NTT a major performance bottleneck due to its intensive polynomial computations. H…
ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge
Yuntao Dai, Hang Gu, Teng Wang +6
Vision-Language-Action (VLA) models have emerged as a unified paradigm for robotic perception and control, enabling emergent generalization and long-horizon task execution. However…