Thread

1. taylorfinley · 1790799418 · focus · HN ↗

   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:&#x2F;&#x2F;gist.github.com&#x2F;birep&#x2F;6f2c8d490c7a29820997d57bd654c351" rel="nofollow">https:&#x2F;&#x2F;gist.github.com&#x2F;birep&#x2F;6f2c8d490c7a29820997d57bd654c3...

   1. alightsoul · 1790800007 · focus · HN ↗

      Please tell me you published your findings even as an issue on the llama.cpp GitHub

      1. otabdeveloper4 · 1790800969 · focus · HN ↗

         Spoiler alert: the problem didn&#x27;t actually get fixed despite the jaw on the floor.

Unofficial Hacker News client; not affiliated with Y Combinator.