home | list info | list archive | date index | thread index

[ovsage-regulars] June Meeting: 2026-06-18 @ 19:00

As you have probably seen from the previous email Devon will be giving an LLM inference engine talk and you are welcome to play/work along with the talk.

Based on what I see in the PDF,  some GPU will probably be necessary and as usual, your mileage will vary. I'll be trying it with an AMD Ryzen processor with embedded  radeon GPU, so who knows how well that will work. I guess I'll find out. I do not expect stellar performance.

message navigation