ernie
I have joined the Ernie team and research on the next generation of architecture design for LLM.
I have joined the Ernie team and research on the next generation of architecture design for LLM.
In collaboration with Li Auto, we explored a hardware co-design law that jointly characterizes model accuracy and inference performance ( arXiv:2602.10377 ).
I have been curating resources for system areas such as Dissys and MLsys .
I have been curating resources for CUDA programming: CUDA .
I have been curating a list of models for code generation: LLMs for Code .