Daniel Hiltgen

@liquorLiu interesting. So our bundled v11 cuda library didn't work on your system, but removing it so it used the v12(?) version you already had installed fixed the problem, and...

I'm sorry you're hitting this. I just double checked and these binaries in 0.1.32 are correctly signed. I uploaded the 5 different runners to Virus Total, which includes Avast, and...

I've submitted a false positive report to Avast. Looks like their turn-around is 48 hours, so hopefully this will be cleared up in a few days.

There's logic to try to figure out hyperthreading based on what's reported in sysfs to ensure we allocate 1 thread per real core, and don't create 2 threads accidentally based...

@sddzcuigc the following might help shed some light... ``` ls /sys/devices/system/cpu/ cat /sys/devices/system/cpu/cpu*/topology/thread_siblings ``` For reference, on a 4-core (8 hyperthread) Intel CPU I see something like this: ``` %...

Could you share some additional information about your system? What GPU do you have? Windows version, nvidia driver version. This might be a software defect, but I've also seen this...

Doing a quick code inspection between 0.1.27 (the version you're running based on error line numbers) and 0.1.29, I see quite a bit of changes have been made upstream in...

Can you share a little more information about your build environment? Which version of MSVC do you have installed? Did you install the C/C++ tools during the MSVC install? Are...

Not directly addressing the Docker image ask, but FYI, we're working on a native Windows install which might suit your needs. It's not quite ready yet, but if you're comfortable...

Ollama is a client-server architecture, and no inference is taking place in the client. That happens in the server. The environment variable CUDA_VISIBLE_DEVICES will only affect the server (`ollama serve`)...