volo

By generating tokens in parallel via iterative denoising, diffusion language models like Mercury 2 match or exceed autoregressive model quality at 10x speed on standard GPUs, eliminating the need for specialized chips like Cerebras and enabling real-time voice agents and long-reasoning applications.

Agentic synthesis of realistic RL environments from real-world usage logs and business knowledge graphs enables training and evaluation that correlates with production performance, with iterative task hardening to maintain learning signal.

Diffusion-based LLMs achieve 1000+ tokens/sec on standard GPUs by generating tokens in parallel, matching or exceeding autoregressive models on specialized hardware like Cerebras while enabling broader deployment.