DiffusionGemma Puts 1000+ tok/s on an RTX 5090
Google's open 26B diffusion model hits 700+ tok/s on consumer GPUs with day-zero vLLM support. Here's what the bidirectional architecture changes for local inference.
#diffusiongemma
1 post
1 post
Google's open 26B diffusion model hits 700+ tok/s on consumer GPUs with day-zero vLLM support. Here's what the bidirectional architecture changes for local inference.