Picture for Daliang Xu

Daliang Xu

Empowering 1000 tokens/second on-device LLM prefilling with mllm-NPU

Add code
Jul 08, 2024
Viaarxiv icon

A Survey of Resource-efficient LLM and Multimodal Foundation Models

Add code
Jan 16, 2024
Viaarxiv icon

LLMCad: Fast and Scalable On-device Large Language Model Inference

Add code
Sep 08, 2023
Figure 1 for LLMCad: Fast and Scalable On-device Large Language Model Inference
Figure 2 for LLMCad: Fast and Scalable On-device Large Language Model Inference
Figure 3 for LLMCad: Fast and Scalable On-device Large Language Model Inference
Figure 4 for LLMCad: Fast and Scalable On-device Large Language Model Inference
Viaarxiv icon