[diffusion] docs: sync snapshot and minimax-h3 subblock features (#38784)

Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
2026-09-10 17:23:43 +08:00
parent 8a6ab89bf0
commit c9c26d56b2
3 changed files with 60 additions and 0 deletions
@@ -84,6 +84,8 @@ loaded component:

 - `resident` keeps the complete component on the accelerator.
 - `component-offload` stores the complete component on CPU between uses.
+- `snapshot-offload` keeps a CPU weight snapshot while the complete component
+  runs on the accelerator, avoiding a weight copy back to CPU after each use.
 - `layerwise-offload` streams the component's declared layers from CPU.

 `COMPONENT` can be an exact `model_index.json` key or one of `all`, `dit`,