Function std::dpm_solver_1_step

&FloatTensor dpm_solver_1_step(
    const &FloatTensor x_cur,
    const &FloatTensor epsPred,
    float alpha_cur,
    float sigma_cur,
    float alpha_next,
    float sigma_next,
)

in log-SNR space. lambda_t = log(alpha_t/sigma_t); order-1 (dpm_solver_1_step) is the paper's eq. 4.3 first-order update. Note this is NOT the same update as ddim_sampler_step — that equivalence holds for the data-prediction form below (dpm_solver_pp_1_step), not this eps-prediction one; see diffusion.sc's header comment.