theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-22 00:38:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1272 from modelscope/zero3-fix

Browse Source 
Support DeepSpeed ZeRO 3
This commit is contained in:
Zhongjie Duan
2026-02-06 16:33:12 +08:00
committed by GitHub
parent abdf66d09e b0bf78e915
commit 1b47e1dc22
26 changed files with 353 additions and 188 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
diffsynth/models/wan_video_dit.py
View File

@@ -5,6 +5,7 @@ import math
from typing import Tuple, Optional
from einops import rearrange
from .wan_video_camera_controller import SimpleAdapter
from ..core.gradient import gradient_checkpoint_forward
try:
import flash_attn_interface
@@ -379,27 +380,15 @@ class WanModel(torch.nn.Module):
self.freqs[1][:h].view(1, h, 1, -1).expand(f, h, w, -1),
self.freqs[2][:w].view(1, 1, w, -1).expand(f, h, w, -1)
], dim=-1).reshape(f * h * w, 1, -1).to(x.device)
def create_custom_forward(module):
def custom_forward(*inputs):
return module(*inputs)
return custom_forward
for block in self.blocks:
if self.training and use_gradient_checkpointing:
if use_gradient_checkpointing_offload:
with torch.autograd.graph.save_on_cpu():
x = torch.utils.checkpoint.checkpoint(
create_custom_forward(block),
x, context, t_mod, freqs,
use_reentrant=False,
)
else:
x = torch.utils.checkpoint.checkpoint(
create_custom_forward(block),
x, context, t_mod, freqs,
use_reentrant=False,
)
if self.training:
x = gradient_checkpoint_forward(
block,
use_gradient_checkpointing,
use_gradient_checkpointing_offload,
x, context, t_mod, freqs
)
else:
x = block(x, context, t_mod, freqs)