[Feat] support for multi-block layerwise offloading, fix top-level parameters/buffers staying on CPU (#1486)

Signed-off-by: Lancer <maruixiang6688@gmail.com>
Signed-off-by: Lancer <402430575@qq.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
This commit is contained in:
LancerandDidan Deng authored and GitHub committed 2026-04-06 11:49:35 +08:00
1 parent e23b2634d1
commit 328de586aa
13 files changed
+288 -38

No files matched your search

@@ -725,7 +725,7 @@ class WanTransformer3DModel(nn.Module):
"""
_repeated_blocks = ["WanTransformerBlock"]
_layerwise_offload_blocks_attr = "blocks"
_layerwise_offload_blocks_attrs = ["blocks"]
packed_modules_mapping = {
"to_qkv": ["to_q", "to_k", "to_v"],
}