Thanks for sending an issue! Please fill in the following template to help quickly solve your problem.
Conv3DDX/DW算子aclnnConvolutionBackward接口使用torch.npu.set_device_limit(device_id, cube_num, vec_num) 设置CV核数，实测V核不受控。
950
使用TurningAclnn测试框架设置cube_aicore_num_limit = 2|3，验证V核不满足配比情况，算子是否正常调用
算子tiling侧拦截，V核不满足无法正常调用
无
Thanks for sending an issue! Please fill in the following template to help quickly solve your problem.
Describe the current behavior / 问题描述 (Mandatory / 必填)
Conv3DDX/DW算子aclnnConvolutionBackward接口使用torch.npu.set_device_limit(device_id, cube_num, vec_num) 设置CV核数，实测V核不受控。
Environment / 环境信息 (Mandatory / 必填)
950
Steps to reproduce the issue / 重现步骤 (Mandatory / 必填)
使用TurningAclnn测试框架设置cube_aicore_num_limit = 2|3，验证V核不满足配比情况，算子是否正常调用
Describe the expected behavior / 预期结果 (Mandatory / 必填)
算子tiling侧拦截，V核不满足无法正常调用
Related log / screenshot / 日志 / 截图 (Mandatory / 必填)
无
Special notes for this issue/备注 (Optional / 选填)