Aunxfb

Trying to Run gpt4all on GPU, Windows 11: RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'

11

Summary: Can't get pass #RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'# Since the error seems to be due to things not being run on GPU(?), I tried: - Add "@jit(target_backend='cuda')" to...