Inception Labs launches Mercury Coder to generate 1,000+ tokens per second with diffusion
Inception Labs just launched Mercury Coder, the first commercial-scale diffusion language model that generates entire code sequences in parallel rather than predicting tokens sequentially. Running on standard Nvidia H100 GPUs, it hits over 1,000 tokens per second while matching models like GPT-4o Mini. Why it matters: It proves text can borrow from image generation to slash AI inference latency and costs tenfold without specialized hardware.