luke
luke
I got it to build but I put ```app-store``` instead of ```app-store-connect``` in my ExportOptions.plist
whats the plan for this sorta thing. is it in the scope of candle. since it does support nearest neighbor should it support others?
Ok so compiling on the A100 works great. It must be a cuda mismatch problem. I did try using the CUDA_COMPUTE_CAP=80 when compiling on my desktop ADA4000 and then running...
When CUDA_VISIBLE_DEVICES is set to the correct device and i can see that the correct GPU is used in ```nvidia-smi -l 1``` realtime monitoring it gets up to about 9GB...
I did a clean and its the same error. I can monitor it in nvidia-smi which card is being used. The older card simply runs out of memory right away....
Actually it is pointing to the right card. it's using the correct card. CUDA_VISIBLE_DEVICES works as it should, there is no problem there. it's using the correct card and crashing....
just checking back in. no idea how to troubleshoot this. so it works on the A100 but still getting the same error on my ADA RTX 4000 with 20GB and...
what is this waiting on?
so does that mean its a clang problem and not a candle/metal problem? this one is for f16 not sure how to troubleshoot?
Just tested here on Mac M1 with ``` MACOSX_DEPLOYMENT_TARGET=15.3 cargo run --example stable-diffusion-3 --release --features=metal -- \ --which 3.5-medium --height 1024 --width 1024 \ --prompt 'lets go' ``` and gets...