😁
I may be slow to respond.
KavioYu
yukavio
Focus on model inference optimization, such as inference engine and model compression.
Shanghai
Yang Yu
reyoung
I am the NLP/LLM infra leader for WeChat,
was a core developer for Paddle.
WeChat LLM Infra Team is hiring! Please feel free to email me.
Tencent Beijing
Chenggang Zhao
LyricZhao
@deepseek-ai infra; previously at NVIDIA | SenseTime | Tsinghua University.
DeepSeek AI Hangzhou, China