Jiakun Fan's picture

1

Jiakun Fan

Vincent-Fan

chosen-ox

AI & ML interests

None yet

Recent Activity

authored a paper 1 day ago

Taming the Memory Footprint Crisis: System Design for Production Diffusion LLM Serving

authored a paper 1 day ago

Parallel CPU-GPU Execution for LLM Inference on Constrained GPUs

upvoted a paper 2 days ago

Parallel CPU-GPU Execution for LLM Inference on Constrained GPUs

View all activity

Organizations

None yet

Papers 2

arxiv:2512.17077

arxiv:2506.03296

models 2

Vincent-Fan/Llama-2-7b-hf-Q4_K_S-GGUF

Text Generation • 7B • Updated Nov 16, 2024

Vincent-Fan/Llama-3.2-1B-Q4_0-GGUF

Text Generation • 1B • Updated Nov 16, 2024 • 2

datasets 0

None public yet