disco4000

OK, I can confirm, that really did the trick. After rebuilding the image, the chat function works, and the UNRAID UI also shows that the P4000 is totally involved. 👍 Unfortunately the image is now bloated up to 60GB on my docker volume. I will post an issue on the localai github space and send the logs to mulder.

I've got the same problem, it seems to be the lack of extensions (AVX2, etc) of our Ivy Bridge XEONS. I followed the build guide and rebuild the CPU only version with the CMAKE arguments in the log and after that the chat option in the WEBUI immediately worked with several different models. Connecting other apps via API to LocalAI worked as well. If I understand Mulder's change logs correct, normaly LocalAI should have all the backends precompiled for non-AVX, AVX and AVX2 and automatically decide which one to use. But this seems to fail, especially when running LocalAI in docker. ATM I'm rebuilding the CUDA12 image without all extension. This will take another 2-3 hours. Lets see if this works afterwards as well.

Hi, the Invoke-AI container is pulling 4,5GB with every update almost every next day. Do all these big files really change everytime there is an update or ist this a misconfiguration in the docker build file? Cheers, d.

OK, in order to capture the diagnostics for both driver installs I reinstalled the v510.68.02 and miraculously this time the card has been recognized after reboot. I did exactly the same thing 3 times before, no success. Now it works.

Anyone got an idea why my P400 is not recognized with the latest Production Branch driver v510.68.02? The info section in the plugin screen remains empty and plex and tdarr won't see the card either (of course). Rolling back to v470.94 and everything is working again. Since this is a Pascal based card which still is fully supported by NVIDIA and the latest Linux drivers on their webpage are also the v510.68.02, I am wondering what the problem is?!

Completely posted it wright, was able to reproduce this. Was attached to vfio at boot and not attached to efifb. You're totally right. Without the plugin the VMs ended up with a black screen after a couple of shutdowns. I ended up reconfiguring the complete setup from scratch and it worked for about 4-5 hours with several VM restarts, but unfortunately the Time-Out error struck again. Since I need the VM for work and can't afford to spend more time on tweaking and testing, I reverted to the Quadro, which still is capable enough for light UI/UX design tasks. If Apple sticks to its usual support cycles, BigSur should receive security updates for another two years. And maybe at that point the ARM transition will already have ended the hackintosh era. 😞

OK, after intensive testing this morning I ended up removing the multifunction config and uninstalling the Vendor Reset plugin. I got a pair of 1st gen Soundsticks via USB connected so I don't need the digital audio output anyway. Besides having only one more crash from the macOS VM (after several boots and shutdowns with other VMs), two other strange things happened: After a reboot into a Windows VM the system console showed this message after initializing the GPU: vfio-pci 0000:05:00.0: Invalid PCI ROM header signature: expecting 0xaa55, got 0xaa55 Another boot into a Windows VM resulted in the infamous Error Code 43 inside the hardware manager Next thing I will do is isolating the respective CPUs I use for my VMs. Maybe this brings it into a state that could be called "acceptable stability".

Hi, I know this kind of issue has been discussed several times with several different solution approaches. Unfortunately none of theses approaches seem to solve my problem. I have a Win10, Win11 and macOS Big Sur VM running completely fine with a NVIDIA Quadro K2000 passed through. Now that Apple decided to end support for Kepler based GPUs in Monterey, I wanted to expand the life of my macOS VM a little more and bought a RX460 on ebay. The GPU is fully functional with the Win VMs on unraid and also works fine with a Monterey VM on a Proxmox Server I do have for testing purposes. But on my unraid server the RX460 in combination with my daily driver macOS VM crashes the host system after having used the VM and trying to start the same or another VM: Windows VM - shutdown and start another VM/reboot - works Ubuntu VM - shutdown and start another VM/reboot - works macOS VM - shutdown and start another VM/reboot - crash same macOS VM with VNC only - shutdown and start another VM/reboot - works What I have done so far: installed ich777s AMD Vendor Reset plugin adjusted the macOS VM xml to use the GPU as a multifunction device added VTI=12 to boot-args I didn't append "pcie_no_flr=1022:149c,1022:1487" since my system does not have any PCI devices with that address The crash completely freezes the system, so I am not able to generate a diagnostics file AFTER starting a VM following a macOS shutdown. But I used unraid's console window to capture this final error which is repeated infinitely: Mar 8 11:40:53 BadBoysUncle kernel: DMAR: Invalidation Time-out Error (ITE) cleared Mar 8 11:40:53 BadBoysUncle kernel: DMAR: VT-d detected Invalidation Time-out Error: SID 0 Mar 8 11:40:53 BadBoysUncle kernel: DMAR: QI HEAD: Device-TLB Invalidation qw0 = 0x50000000003, qw1 = 0x87fff001 Mar 8 11:40:53 BadBoysUncle kernel: DMAR: QI PRIOR: Invalidation Wait qw0 = 0x200000025, qw1 = 0x1001510cc I also attached a diagnostics file that has been created after a shutdown of the macOS VM. Maybe someone is able to help. Thanks, d. badboysuncle-diagnostics-20220308-1008.zip

Mission accomplished. The Inateck arrived half an hour ago, and everything went smooth as silk: Install->Bind to VFIO->Select in VM->Soundsticks playing perfectly. Update: Avoid installing the genuine Inateck drivers for Windows with this device in a VM. It will interfere with the PCIe device reset and cause error 127. The generic Microsoft driver works fine.

Just gave that a shot. My Z420 has 3 USB controllers, 2 Intel Chipset C600/X79 series 2.0 and one Texas Instruments TUSB73x0 SuperSpeed USB 3.0 controller. Unfortunately the TUSB73x0 is not recognised as a USB controller by macOS due to the lack of appropriate drivers. Moving the unRAID flash drive to the front USB port, I was able to bind the rear ports of the C600 to VFIO and pass it through to the VMs. Again mixed results are my problem: It works perfectly fine under Windows together with the passed through K2000 Passing through GPU and USB in a macOS VM refuses to boot, black screen Passing through USB and using VNC makes the macOS VM boot again, show the C600 in system profiler, but only the controller, no devices This is really kind of a hit&miss game. I just ordered an Inateck USB PCIe card. According to tonymacx86 the FL1100 chipset on this card is fully supported by macOS. Lets see when it arrives tomorrow. Same result, didn't change anything.

Hi guys, as a 25 years Mac user and former SysAdmin I loved the idea of having a macOS VM on my unRAID Server and spent the last days making it fully capable of being my daily driver. I struggled with different things on my way, including a very restive Quadro K2000 refusing to make GPU passthrough working, although working fine as a standalone card in another rig. I finally managed to make this grouch work via BIOS update, the last resort I was willing to give this card. Anyway, there is one last thing that is preventing this setup from being perfect: my Harman Kardon Soundsticks (first Rev., with software controlled volume). They are showing up correctly in system devices on unRAID and macOS SystemProfiler displays them the same as on a baremetal system. But the sound is distorted and discontinuous. It sounds like the bandwidth of the USB port wouldn't be sufficient and therefore be interrupted. I tried all the usual things: check MidiSettings for sampling rate put the Sticks on a separate USB port try with 2.0 and 3.0 USB ports uncheck all other devices in unRAIDs VM settings to make the USB controller exclusive to the Sticks some other weird things I can't recall But worst of all: the same setup is working completely fine under Windows! I even daisy-chained the Sticks through a USB selector and an active hub and they still played perfect with Redmond-Ware. Having read through several, mostly outdated threads in other forums, there has been no real clue about why macOS seems to handle the data transfer for this DAC differently. There have been some hints about timings, but no real information to make this work. If anyone out there in this community has some idea that could help, I would really appreciate any answer here. Thanks in advance, d.

Awesome, working out of the box! Thank you sooo much.

Great, I will be looking forward to this release.

Hi ich777, I tried to run your xlinkkaievolution docker on my unRAID 6.8.2 server, adding the following to the extra parameters input field: --env 'UMASK=000' --env 'UID=99' --env 'GID=100' --cap-add NET_ADMIN --restart=unless-stopped The network type is 'Host' and the privileged toggle is set ON. The docker tab reports the docker image as running successfully but the WebUI is not responding on Port 34522. Maybe you could give some more information how to run this docker in unRAID. Thanks in advance, disco