I asked Codex to optimize DeepSeek V4 Flash 8-bit MLX on oMLX. Got ~1.6x prefill and ~3x decode speedup. | 入行 365 深度情报

正在加载入行工作台

I asked Codex to optimize DeepSeek V4 Flash 8-bit MLX on oMLX. Got ~1.6x prefill and ~3x decode speedup. | 入行 365 深度情报 | 入行 365 旗下的「入行之路」