Skip to content

[pull] master from comfyanonymous:master #106

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 1 commit into from
Jun 9, 2025
+6 −1
Merged

[pull] master from comfyanonymous:master #106

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 6 additions & 1 deletion comfy/model_management.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -295,6 +295,7 @@ def is_amd():
pass


SUPPORT_FP8_OPS = args.supports_fp8_compute
try:
if is_amd():
try:
Expand All @@ -308,6 +309,10 @@ def is_amd():
if torch_version_numeric >= (2, 7): # works on 2.6 but doesn't actually seem to improve much
if any((a in arch) for a in ["gfx1100", "gfx1101", "gfx1151"]): # TODO: more arches
ENABLE_PYTORCH_ATTENTION = True
if torch_version_numeric >= (2, 7) and rocm_version >= (6, 4):
if any((a in arch) for a in ["gfx1201"]): # TODO: more arches
SUPPORT_FP8_OPS = True

except:
pass

Expand Down Expand Up @@ -1262,7 +1267,7 @@ 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:
if SUPPORT_FP8_OPS:
return True

if not is_nvidia():
Expand Down
Loading