OpenAI used GPT-5.6 Sol to optimize the model's forward pass and autonomously rewrite production kernels in Triton and Gluon, reducing end-to-end serving costs by 20%.

We also used GPT‑5.6 Sol to optimize the model's forward pass: the computation that transforms inputs into next-token predictions. Even when individual operations are fast, excess memory movement, synchronization, and inefficient data layouts can leave GPUs idle. To avoid this, GPT‑5.6 Sol found work that could be precomputed, avoided, or parallelized. With Codex, GPT‑5.6 Sol autonomously rewrote and optimized our production kernels, the core code that executes the mathematical operations that make up the model. This worked in part because we've trained GPT‑5.6 to be effective at writing and improving kernels in Triton and Gluon, two open-source GPU programming languages maintained by OpenAI. These efforts, combined with broader kernel advancements from GPT‑5.6 Sol, reduced end-to-end serving costs by 20%.

Read full article ↗excerpt · fair-use quotation