Skip to content

fix: prevent autocast crash with fp8 weights in WAN model addcmul ops (CORE-47) #13343

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
deepme987 wants to merge 2 commits into from
+22 −11
Closed

fix: prevent autocast crash with fp8 weights in WAN model addcmul ops (CORE-47) #13343

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7db81e4
fix: prevent autocast crash in WAN model addcmul ops
deepme987 Apr 10, 2026
ec913cc
fix: convert run_intel_gpu.bat line endings from CRLF to LF
deepme987 Apr 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions .ci/windows_intel_base_files/run_intel_gpu.bat
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
pause
.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
pause
29 changes: 20 additions & 9 deletions comfy/ldm/wan/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -174,6 +174,17 @@ def repeat_e(e, x):
return torch.repeat_interleave(e, repeats + 1, dim=1)[:, :x.size(1)]


def _addcmul(x, y, z):
"""torch.addcmul wrapper that disables autocast to prevent
'Unexpected floating ScalarType in at::autocast::prioritize' when
upstream nodes (e.g. SAM3) leave CUDA autocast enabled."""
device_type = x.device.type
if torch.is_autocast_enabled(device_type):
with torch.autocast(device_type=device_type, enabled=False):
return torch.addcmul(x, y, z)
return torch.addcmul(x, y, z)


class WanAttentionBlock(nn.Module):

def __init__(self,
Expand Down Expand Up @@ -242,10 +253,10 @@ def forward(
# self-attention
x = x.contiguous() # otherwise implicit in LayerNorm
y = self.self_attn(
torch.addcmul(repeat_e(e[0], x), self.norm1(x), 1 + repeat_e(e[1], x)),
_addcmul(repeat_e(e[0], x), self.norm1(x), 1 + repeat_e(e[1], x)),
freqs, transformer_options=transformer_options)

x = torch.addcmul(x, y, repeat_e(e[2], x))
x = _addcmul(x, y, repeat_e(e[2], x))
del y

# cross-attention & ffn
Expand All @@ -255,8 +266,8 @@ def forward(
for p in patches["attn2_patch"]:
x = p({"x": x, "transformer_options": transformer_options})

y = self.ffn(torch.addcmul(repeat_e(e[3], x), self.norm2(x), 1 + repeat_e(e[4], x)))
x = torch.addcmul(x, y, repeat_e(e[5], x))
y = self.ffn(_addcmul(repeat_e(e[3], x), self.norm2(x), 1 + repeat_e(e[4], x)))
x = _addcmul(x, y, repeat_e(e[5], x))
return x


Expand Down Expand Up @@ -371,7 +382,7 @@ def forward(self, x, e):
else:
e = (comfy.model_management.cast_to(self.modulation, dtype=x.dtype, device=x.device).unsqueeze(0) + e.unsqueeze(2)).unbind(2)

x = (self.head(torch.addcmul(repeat_e(e[0], x), self.norm(x), 1 + repeat_e(e[1], x))))
x = (self.head(_addcmul(repeat_e(e[0], x), self.norm(x), 1 + repeat_e(e[1], x))))
return x


Expand Down Expand Up @@ -1453,17 +1464,17 @@ def forward(

# self-attention
y = self.self_attn(
torch.addcmul(repeat_e(e[0], x), self.norm1(x), 1 + repeat_e(e[1], x)),
_addcmul(repeat_e(e[0], x), self.norm1(x), 1 + repeat_e(e[1], x)),
freqs, transformer_options=transformer_options)

x = torch.addcmul(x, y, repeat_e(e[2], x))
x = _addcmul(x, y, repeat_e(e[2], x))

# cross-attention & ffn
x = x + self.cross_attn(self.norm3(x), context, context_img_len=context_img_len, transformer_options=transformer_options)
if audio is not None:
x = self.audio_cross_attn_wrapper(x, audio, transformer_options=transformer_options)
y = self.ffn(torch.addcmul(repeat_e(e[3], x), self.norm2(x), 1 + repeat_e(e[4], x)))
x = torch.addcmul(x, y, repeat_e(e[5], x))
y = self.ffn(_addcmul(repeat_e(e[3], x), self.norm2(x), 1 + repeat_e(e[4], x)))
x = _addcmul(x, y, repeat_e(e[5], x))
return x

class DummyAdapterLayer(nn.Module):
Expand Down
Loading