Ten days ago I had an experience with Gemini 3.8 flash that made me wonder if I was being routed to a different model under test. I was trying to use rocm with llama.cpp on my 128gb Strix Halo but could only get it to run Vulkan. I pasted the error message into agy and it proceeded to attach GDB to my GPU driver, reverse-engineer the kernel queue ioctl interface, and author an LD_PRELOAD C shim to get ROCm llama.cpp working on my Strix Halo. My jaw was hanging open the whole time.
Edit to add the fix: <a href="https://gist.github.com/birep/6f2c8d490c7a29820997d57bd654c351" rel="nofollow">https://gist.github.com/birep/6f2c8d490c7a29820997d57bd654c3...
That's cool, but the real question is, why aren't you using Hipfire[1] or HaloPFX[2]? Both are far superior to llama.cpp in terms of performance, for Strix Halo.
taylorfinley · · focus · HN ↗
Edit to add the fix: <a href="https://gist.github.com/birep/6f2c8d490c7a29820997d57bd654c351" rel="nofollow">https://gist.github.com/birep/6f2c8d490c7a29820997d57bd654c3...
d3Xt3r · · focus · HN ↗
[1] <a href="https://github.com/warpfront/hipfire" rel="nofollow">https://github.com/warpfront/hipfire
[2] <a href="https://github.com/julianmb/halofpx" rel="nofollow">https://github.com/julianmb/halofpx