Proxmox - PCIe passthrough - Nvidia - Tesla - P40 as Host device
Budget: ₹600 – ₹1,500 INR
I am looking for a freelancer who has experience with Proxmox and PCIe passthrough for Nvidia Tesla P40. The primary purpose of the passthrough is for "Other" (client to specify).
Ideal Skills and Experience:
- Proxmox expertise, specifically with version 8.0.4
- Experience with Nvidia Tesla P40 GPU installation on Proxmox server
- Proficient in configuring and implementing PCIe passthrough
- Understanding of virtual machine GPU acceleration and related technologies
We have already did the pcie as RAW device / Host :
lspci -nnk | grep -i nvidia -A2
37:00.0 3D controller [0302]: NVIDIA Corporation GP102GL [Tesla P40] [10de:1b38] (rev a1)
Subsystem: NVIDIA Corporation GP102GL [Tesla P40] [10de:11d9]
Kernel driver in use: vfio-pci
Kernel modules: nvidiafb, nouveau
5b:00.0 PCI bridge [0604]: Intel Corporation Sky Lake-E PCI Express Root Port A [8086:2030] (rev 04)
Subsystem: Hewlett Packard Enterprise Sky Lake-E PCI Express Root Port A [1590:00ea]
--
af:00.0 3D controller [0302]: NVIDIA Corporation GP102GL [Tesla P40] [10de:1b38] (rev a1)
Subsystem: NVIDIA Corporation GP102GL [Tesla P40] [10de:11d9]
Kernel driver in use: vfio-pci
Kernel modules: nvidiafb, nouveau
d7:00.0 PCI bridge [0604]: Intel Corporation Sky Lake-E PCI Express Root Port A [8086:2030] (rev 04)
Subsystem: Hewlett Packard Enterprise Sky Lake-E PCI Express Root Port A [1590:00ea]
But when we use NVIDIA-SMI : NVIDIA-SMI has failed because it couldn't communicate with the NVIDIA driver. Make sure that the latest NVIDIA driver is installed and running.
DMESG : NVRM: This PCI I/O region assigned to your NVIDIA device is invalid:
NVRM: BAR0 is 0M @ 0x0 (PCI:0000:01:00.0)
nvidia: probe of 0000:01:00.0 failed with error -1
NVRM: The NVIDIA probe routine failed for 1 device(s).
NVRM: None of the NVIDIA devices were initialized.
nvidia-nvlink: Unregistered Nvlink Core, major device number 238
If you have the necessary skills and experience with Proxmox, Nvidia Tesla P40, and PCIe passthrough, please reach out to discuss the project further.
Ideal Skills and Experience:
- Proxmox expertise, specifically with version 8.0.4
- Experience with Nvidia Tesla P40 GPU installation on Proxmox server
- Proficient in configuring and implementing PCIe passthrough
- Understanding of virtual machine GPU acceleration and related technologies
We have already did the pcie as RAW device / Host :
lspci -nnk | grep -i nvidia -A2
37:00.0 3D controller [0302]: NVIDIA Corporation GP102GL [Tesla P40] [10de:1b38] (rev a1)
Subsystem: NVIDIA Corporation GP102GL [Tesla P40] [10de:11d9]
Kernel driver in use: vfio-pci
Kernel modules: nvidiafb, nouveau
5b:00.0 PCI bridge [0604]: Intel Corporation Sky Lake-E PCI Express Root Port A [8086:2030] (rev 04)
Subsystem: Hewlett Packard Enterprise Sky Lake-E PCI Express Root Port A [1590:00ea]
--
af:00.0 3D controller [0302]: NVIDIA Corporation GP102GL [Tesla P40] [10de:1b38] (rev a1)
Subsystem: NVIDIA Corporation GP102GL [Tesla P40] [10de:11d9]
Kernel driver in use: vfio-pci
Kernel modules: nvidiafb, nouveau
d7:00.0 PCI bridge [0604]: Intel Corporation Sky Lake-E PCI Express Root Port A [8086:2030] (rev 04)
Subsystem: Hewlett Packard Enterprise Sky Lake-E PCI Express Root Port A [1590:00ea]
But when we use NVIDIA-SMI : NVIDIA-SMI has failed because it couldn't communicate with the NVIDIA driver. Make sure that the latest NVIDIA driver is installed and running.
DMESG : NVRM: This PCI I/O region assigned to your NVIDIA device is invalid:
NVRM: BAR0 is 0M @ 0x0 (PCI:0000:01:00.0)
nvidia: probe of 0000:01:00.0 failed with error -1
NVRM: The NVIDIA probe routine failed for 1 device(s).
NVRM: None of the NVIDIA devices were initialized.
nvidia-nvlink: Unregistered Nvlink Core, major device number 238
If you have the necessary skills and experience with Proxmox, Nvidia Tesla P40, and PCIe passthrough, please reach out to discuss the project further.