Latest (0.1.27) docker image with ROCm works for me on Ryzen 5600G with 8GB VRAM allocation. Prompt processing is 2x faster than with CPU. Generation runs at max speed even if CPU is busy running other processes. I am on Fedora 39. Container setup: HSA_OVERRIDE_GFX_VERSION=9.0.0
Use this to install ROCm on Tumbleweed. Does NOT talk about Pytorch, the tag is for completeness.
This (and every) answer should make it clear that it is not possible to do this in free space, but occurs in interaction with a material medium.
They describe using Bell-Theorem-like inequality to refute a real-numbers-only quantum theory is equivalent to imaginary-numbers quantum theory
Try this to install ROCm v 4.something. Use Kernel up to 5.4 to be safe (5.4 started in 2020)
forum of DEBIAN TEAM WORKING ON ROCM PACKAGING
AMD's repo of Pytorch. This is the branch I succesfully built.
NON-passmark comparisons of GPU. Vega 8 is better than Vega 7.
