multiplication

The passage around this formula

against the cost of simply continuing to serve the teacher directly for the same query volume, $TC_{\mathrm{teacher}} = Q \cdot c_{\mathrm{teacher}}$. Here $C_{\mathrm{distill}}$ is the one-time training cost, Q is the number of queries served over the deployment’s life, and $c_{\mathrm{student}}$ and $c_{\mathrm{teacher}}$ are the marginal cost per query of serving each model, wherever that serving happens. The break-even query volume is

Read this part in the article →