Skip to content

[pull] master from comfyanonymous:master #75

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

Merged
merged 2 commits into from
May 23, 2025
Merged

[pull] master from comfyanonymous:master #75

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
30b2eb8
create arange on-device (#8255)
drhead May 23, 2025
0b50d4c
Add argument to explicitly enable fp8 compute support. (#8257)
comfyanonymous May 23, 2025
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
1 change: 1 addition & 0 deletions comfy/cli_args.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,6 +88,7 @@ def __call__(self, parser, namespace, values, option_string=None):

parser.add_argument("--oneapi-device-selector", type=str, default=None, metavar="SELECTOR_STRING", help="Sets the oneAPI device(s) this instance will use.")
parser.add_argument("--disable-ipex-optimize", action="store_true", help="Disables ipex.optimize default when loading models with Intel's Extension for Pytorch.")
parser.add_argument("--supports-fp8-compute", action="store_true", help="ComfyUI will act like if the device supports fp8 compute.")

class LatentPreviewMethod(enum.Enum):
NoPreviews = "none"
Expand Down
2 changes: 1 addition & 1 deletion comfy/ldm/chroma/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -163,7 +163,7 @@ def forward_orig(
distil_guidance = timestep_embedding(guidance.detach().clone(), 16).to(img.device, img.dtype)

# get all modulation index
modulation_index = timestep_embedding(torch.arange(mod_index_length), 32).to(img.device, img.dtype)
modulation_index = timestep_embedding(torch.arange(mod_index_length, device=img.device), 32).to(img.device, img.dtype)
# we need to broadcast the modulation index here so each batch has all of the index
modulation_index = modulation_index.unsqueeze(0).repeat(img.shape[0], 1, 1).to(img.device, img.dtype)
# and we need to broadcast timestep and guidance along too
Expand Down
3 changes: 3 additions & 0 deletions comfy/model_management.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1257,6 +1257,9 @@ def should_use_bf16(device=None, model_params=0, prioritize_performance=True, ma
return False

def supports_fp8_compute(device=None):
if args.supports_fp8_compute:
return True

if not is_nvidia():
return False

Expand Down
Loading