← 返回事件
持续讨论AI发版

trunk/1021ddaa95dbaec8775442af63d998591b50a353: Key sparse Triton tuning tables by the current accelerator (#194176)

图:PyTorch Releases

发生了什么

Related to this RFC: #194355 Summary _get_device_name() supplies the device component of the key under which _operation_device_version_data stores tuned Triton parameters. It was a two-branch chain over torch.cuda and torch.xpu returning "" for anything else, and it took no arguments -- so the key named whatever the process was configured for, never the device the inputs were actually on. An accelerator outside that…

摘要按规则整理自下方来源原文

为什么在扩散

来源