Alex Cheema
Alex Cheema
Do you mean running mining workloads using exo or repurposing mining hardware as GPUs for AI workloads using exo?
@samiamjidkhan can you take a look please. We will remove the network setup script soon (I think). So main thing is looking into removing the plist cleanly and robustly.
Would definitely suggest trying with a TB5 cable.
> I'm seeing the same behavior on our cluster; 4 M3 Ultra Mac Studios running on macOS 26.2 connected via TB5 with RDMA enabled. The Qwen3 models just stay stuck...
@RWL-Dittrich @kshaffer-bf I just pushed a hotfix that attempts to fix this. Can you go into your EXO macOS app and click "Check For Updates" and update to `1.0.60` and...
Would you like support for any specific vision model? Would this be something you want control over to choose which vision model is used to parse the PDF?
> Is anyone assigned/working on it?, if not I can give it a try. Sounds interesting to me. Assigned. Best of luck.
GPU passthrough is not supported on macOS, which is our primary deployment target. I would be open to a Linux-based docker image. This should be fairly easy to add. But...
Thanks for flagging this. Currently we are not using svelte optimally. I believe we are trigger a full re-render of the page every time we fetch the state, which shouldn't...
Apologies @andrewwutw @aaronysl it looks like there were quite a few regressions in 1.0.61/1.0.62. Stick to 1.0.60 for now and we will fix these in 1.0.63.