As i currently use an intel arc for av1 encoding and decoding on my server, i currently use slow cpu processing for ollama 1.5b, and would prefer proper gpu accel for bigger models, is there a integration for a llm host that has arc support?
#Is there a llm assistant tool/docker yet that has full intel arc support yet?
rugged sequoia
ionic mountain
As i currently use an intel arc for av1 encoding and decoding on my server, i cu...
ollama got vulkan support sorted out semi recently didn't they? you should be able to use the arc with vulkan I think?