Exciting news! vLLM is starting a special interest group for local AI.
If you're on the vLLM slack, join #sig-local-ai# with us and help drive vLLM forward on local AI hardware: DGX Spark, AMD Strix Halo (and hey, even @SipeedLab!).
Show more
It's a little disappointing to see our hard work end up in someone's packaged product without even a mention. I appreciate that the upstream package for this does credit our work, but this guy is just repackaging something, stripping detailed attribution and then calling his own?
Show more
The _most_ important use-case (more than hotdog-or-not!) for DiffusionGemma-as-Jev's image stack: categorizing food by the number of sides in under half a second each.
I ran some real, live evals on Jev vs DiffusionGemma-as-Jev (my patch for vLLM!)
DiffusionGemma comes out as the winner, I think.
Headlines:
Is Jev faster than DiffusionGemma? No ❌ (API vs DGX Spark)
Is Jev smarter than DiffusionGemma? No ❌ (they're roughly tied!)
Show more
