viable/strict/1792101043: Fix PagedAttention defaulting to CUDA on non-CUDA accelerators (#196191)

发生了什么

Summary PagedAttention.__init__ defaulted device to the literal string "cuda" , even though nothing else in the class is CUDA-specific: every tensor allocation already threads the device parameter through generically ( torch.ones/zeros(..., device=device) ), and later methods ( reserve , convert_logical_block_mask ) derive their device from existing tensors rather than hardcoding anything. The class is already exerc…

摘要按规则整理自下方来源原文

来源