这个内容已经在X上讨论过了, 很火热的问题 我先翻译一下国外教授的详细回答,再讲清楚CUDA、PTX的关系。 中文翻译: 人们说“Deepseek 使用了 PTX ...
The breakthrough was achieved by implementing tons of fine-grained optimizations and usage of assembly-like PTX (Parallel Thread Execution) programming instead of Nvidia's CUDA, according to an ...