Question 1

Why do FLUX cold starts take so long?

Accepted Answer

Production diffusion serving pins fixed resolutions for compiled performance, and each resolution triggers its own torch.compile pass. With max-autotune and an exhaustive GEMM autotune search, 11 resolutions pushed FLUX's native cold start to roughly 50 minutes on 8x NVIDIA B200: weights load in seconds, but the pipeline is not ready to serve until every resolution's kernels are compiled and tuned.

Question 2

Does Cedana restore skip torch.compile?

Accepted Answer

Yes. Compiled artifacts, autotune results, and the fully initialized pipeline are all part of the workload's execution state, so a Cedana restore brings back the ready-to-serve pipeline in 73 seconds without redoing any compilation. Restore time is independent of how much compilation work went into the checkpoint.

Question 3

Does this work for other diffusion and video models?

Accepted Answer

The mechanism transfers to any pipeline with per-resolution or per-shape compilation, including SDXL, Stable Diffusion 3.5, and video models such as Wan and HunyuanVideo. FLUX is the measured result; the compilation mechanics are the same, and more compilation work makes the native cold start longer while Cedana restore stays roughly constant.

FLUX diffusion cold start: 50 minutes to 73 seconds