• Members 23 posts
    2026年6月22日 16:46

    我在我的一台8卡C500服务器,执行dmesg -T | grep -i err
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO mxc500_shader_error_queue_handler, handle the int err only first time, hw_queue:0x3
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO mxc500_shader_error_queue_handler, handle the int err only first time, hw_queue:0x3
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO mxc500_shader_error_queue_handler, handle the int err only first time, hw_queue:0x3
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO mxc500_shader_error_queue_handler, handle the int err only first time, hw_queue:0x3
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO mxc500_shader_error_queue_handler, handle the int err only first time, hw_queue:0x3
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO mxc500_shader_error_queue_handler, handle the int err only first time, hw_queue:0x3
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B4F00.D0.XCORE.INFO EID (0000:4f:00.0): 0x2102, shader exception, pasid 33195 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO mxc500_shader_error_queue_handler, handle the int err only first time, hw_queue:0x3
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5000.D0.XCORE.INFO EID (0000:50:00.0): 0x2102, shader exception, pasid 33194 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3C00.D0.XCORE.INFO EID (0000:3c:00.0): 0x2102, shader exception, pasid 33198 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B2E00.D0.XCORE.INFO EID (0000:2e:00.0): 0x2102, shader exception, pasid 33199 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B3F00.D0.XCORE.INFO EID (0000:3f:00.0): 0x2102, shader exception, pasid 33193 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5F00.D0.XCORE.INFO EID (0000:5f:00.0): 0x2102, shader exception, pasid 33196 error_type mem_viol(0x4)
    [日 6月 21 14:37:36 2026] METAX.B5E00.D0.XCORE.INFO EID (0000:5e:00.0): 0x2102, shader exception, pasid 33197 error_type mem_viol(0x4)

    一直重复刷新,这是个什么错误?下面还有一堆,全是这样的

  • arrow_forward

    Thread has been moved from 公共.

  • Members 650 posts
    2026年6月22日 16:53

    尊敬的开发者您好,请详细描述您的操作过程

  • Members 23 posts
    2026年6月22日 16:55

    启动模型,模型命令:
    cat docker-compose-qwen122-ray.yaml
    version: '3.8'

    services:
    qwen3.5-122b-a10b:
    image: cr.metax-tech.com/public-ai-release/maca/vllm-metax:0.19.0-maca.ai3.5.3.502-torch2.8-py310-kylinv11-amd64
    container_name: qwen3.5-122b-a10b
    network_mode: host
    shm_size: 200gb
    privileged: true
    devices:
    - /dev/dri
    - /dev/mxcd
    - /dev/mem
    group_add:
    - video
    security_opt:
    - seccomp=unconfined
    - apparmor=unconfined
    ulimits:
    memlock: -1
    environment:
    - GLOO_SOCKET_IFNAME=enp184s0f1np1
    - MCCL_IB_HCA=rocep75s0f1
    - MACA_DIRECT_DISPATCH=1
    - MACA_SMALL_PAGESIZE_ENABLE=1
    volumes:
    - /usr/local/:/usr/local/
    - /mnt/data/models:/mnt/data/models
    command: >
    /bin/bash -c "ray start --address='192.168.100.236:6379' --num-gpus=8 && tail -f /dev/null"
    restart: always

    主节点236是没有硬件报错,就是因为ray集群一直崩溃,排查到237辅节点有这个报错的

  • Members 23 posts
    2026年6月22日 16:56

    [一 6月 22 15:40:29 2026] MXCD.B3C00.D0.RINGBUF.ERROR EID (0000:3c:00.0): 0x2201, destroy ce ringbuf failed, logic rb_id:3, pipe_id:1
    [一 6月 22 15:40:29 2026] MXCD.B3C00.D0.RINGBUF.ERROR results in a decrease in the number of available ringbufs, ret 1
    [一 6月 22 15:41:03 2026] METAX.B3C00.D0.XCORE.ERROR EID (0000:3c:00.0): 0x2103, kill queue timeout, pipe 2, queue 3
    [一 6月 22 15:41:03 2026] METAX.B2D00.D0.XCORE.ERROR gpu_id:28956, ctrl:0x106000
    [一 6月 22 15:41:03 2026] METAX.B2E00.D0.XCORE.ERROR gpu_id:32860, ctrl:0x106000
    [一 6月 22 15:41:03 2026] METAX.B3C00.D0.XCORE.ERROR gpu_id:11728, ctrl:0x106000
    [一 6月 22 15:41:03 2026] METAX.B3F00.D0.XCORE.ERROR gpu_id:56464, ctrl:0x106000
    [一 6月 22 15:41:03 2026] METAX.B4F00.D0.XCORE.ERROR gpu_id:14517, ctrl:0x106000
    [一 6月 22 15:41:03 2026] METAX.B5000.D0.XCORE.ERROR gpu_id:253, ctrl:0x106000
    [一 6月 22 15:41:03 2026] METAX.B5E00.D0.XCORE.ERROR gpu_id:25721, ctrl:0x106000
    [一 6月 22 15:41:03 2026] METAX.B5F00.D0.XCORE.ERROR gpu_id:62648, ctrl:0x106000

    还有这个错误也一直在重复

  • Members 650 posts
    2026年6月22日 17:05

    尊敬的开发者您好,请停止ray服务尝试,ray后端已不适配,切换MP分布式后端

  • Members 23 posts
    2026年6月23日 15:31

    vllm哪个版本开始不适配的?

  • Members 650 posts
    2026年6月23日 16:31

    尊敬的开发者您好,大概今年发布的版本,vllm-MetaX不适配ray后端

  • Members 23 posts
    2026年6月23日 16:32

    我用的是0.17.0的版本,应该不是ray导致的吧,现在我换了mp后端了,还是会崩溃,等下次崩溃我把日志贴出来,之前很正常,这两周模型使用过程中一直崩溃,不存在大量请求或者异常请求

  • Members 650 posts
    2026年6月23日 16:34

    尊敬的开发者您好,请单机分别跑模型,然后再测双机MCCL,IB Write打流定位问题

  • arrow_forward

    Thread has been moved from 解决中.