Your system BIOS isn’t assigning device memory in a way that allows two 32 GB graphics apertures to fit in the physical address space. These GPUs are designed to go in special server-class motherboards that are tested to work in this configuration so I think you may just be out of luck trying to use them in normal desktop or workstation systems.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| NVRM: This PCI I/O region assigned to your NVIDIA device is invalid | 39 | 18268 | October 12, 2021 | |
| RmInitAdapter failed for two out of four Tesla T4 | 4 | 1705 | December 24, 2021 | |
| Ubuntu tesla P40 NVRM: GPU 0000:03:00.0: RmInitAdapter | 4 | 1525 | March 31, 2023 | |
| 2 cards issue | 4 | 8957 | February 7, 2019 | |
| Nvidia-driver doesn't seem to recognize the second GPU | 14 | 5059 | April 20, 2021 | |
| NVRM: RmInitAdapter failed! - ETH mining server | 8 | 13615 | October 12, 2021 | |
| Only 7 of 8 GPUs are loaded: Dual GRID M40's on HP Proliant DL580 G7 Ubuntu 16.04.5 Server | 3 | 1123 | October 12, 2021 | |
| "RmInitAdapter failed!" Dell R740XD and NVIDIA Tesla T4 | 1 | 305 | April 24, 2024 | |
| Tesla K80 detected on OpenSuse 15.5, but nvidia-smi couldn't communicate with the NVIDIA driver | 8 | 1545 | June 18, 2023 | |
| 8x Tesla M40 on Ubuntu Server 24.04 "Failed to allocate NvKmsKapiDevice" | 5 | 575 | January 2, 2025 |