I can see a scenario where we no longer need to dedicate a physical GPU to a VM with passthru (say to use a windows game/program which cannot run on Linux) and instead split the GPU between the host Linux and the VM.
I wonder if this can be done dynamically, ie. you do that only when you start the VM.
I could be wrong about this but I think it is always dynamic
I’m also really interested in virtio GPU as it seems fairly vendor independent. All it does is provide a virtual GPU that then passes the calls down to the GPU driver of the host
I can see a scenario where we no longer need to dedicate a physical GPU to a VM with passthru (say to use a windows game/program which cannot run on Linux) and instead split the GPU between the host Linux and the VM.
I wonder if this can be done dynamically, ie. you do that only when you start the VM.
I could be wrong about this but I think it is always dynamic
I’m also really interested in virtio GPU as it seems fairly vendor independent. All it does is provide a virtual GPU that then passes the calls down to the GPU driver of the host