Shawn Wang
@swyx
deepseek posted way more alpha on their zhihu page, if you only read twitter you are reading the laowai approved stuff
"Based on this framework, we have implemented a high-throughput, low-latency large-scale inference service for DeepSeek V4.1 Flash. Currently, the service https://t.co/D2pLGs3JR8 https://t.co/E35YHXeei4
