10 papers
Efficient On-Device Diffusion LLM Inference with Mobile NPU
Tuowei Wang, Yanfan Sun, Ju Ren
Diffusion large language models (dLLMs) accelerate generation by denoising multiple tokens in parallel, making them attractive for latency-sensitive mobile inference. However, repe…
Lever: Speculative LLM Inference on Smartphones
Tuowei Wang, Fengzu Li, Yanfan Sun +2
Large language models (LLMs) are increasingly needed for interactive mobile applications, but high-quality models exceed the limited DRAM available on smartphones. Flash storage ca…
Mosaic: Cross-Modal Clustering for Efficient Video Understanding
Tuowei Wang, He Zhou, Chengru Song +2
Large vision-language models (VLMs) are enabling interactive video reasoning, giving rise to streaming long-video understanding. In this setting, frames arrive continuously, while…
Swarm: Co-Activation Aware KVCache Offloading Across Multiple SSDs
Tuowei Wang, Liyun Chu, Ruwen Fan +1
The key-value (KV) cache has become the dominant contributor to memory consumption in large language model (LLM) inference. Although offloading KVCache from GPU high-bandwidth memo…
DynaKV: Enabling Accurate and Efficient Long-Sequence LLM Decoding on Smartphones
Tuowei Wang, Minxing Huang, Fengzu Li +3
As the demand for human-like reasoning, multi-turn dialogues, and long-form responses grows, large language models (LLMs) are increasingly expected to support efficient and effecti…
Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity
Tuowei Wang, Kun Li, Zixu Hao +5
The adaptation of pre-trained large language models (LLMs) to diverse downstream tasks via fine-tuning is critical for numerous applications. However, the inefficiency of parameter…