mirrors/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-05-05 05:46:12 +02:00
Code Issues Actions 20 Packages Projects Releases Wiki Activity

Improve AMD performance. (#10302)
Some checks failed
Python Linting / Run Ruff (push) Has been cancelled
Details
Python Linting / Run Pylint (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.9, [self-hosted Linux], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.10, [self-hosted macOS], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.11, [self-hosted macOS], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.12, [self-hosted macOS], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.9, [self-hosted macOS], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, --use-pytorch-cross-attention, macos, 3.11, [self-hosted macOS], nightly) (push) Has been cancelled
Details
Execution Tests / test (macos-latest) (push) Has been cancelled
Details
Execution Tests / test (ubuntu-latest) (push) Has been cancelled
Details
Execution Tests / test (windows-latest) (push) Has been cancelled
Details
Test server launches without errors / test (push) Has been cancelled
Details
Unit Tests / test (macos-latest) (push) Has been cancelled
Details
Unit Tests / test (ubuntu-latest) (push) Has been cancelled
Details
Unit Tests / test (windows-2022) (push) Has been cancelled
Details
Close stale issues / stale (push) Has been cancelled
Details

Browse Source 
I honestly have no idea why this improves things but it does.
This commit is contained in:
comfyanonymous 2025-10-11 21:28:01 -07:00 committed by GitHub
parent 84e9ce32c6
commit a125cd84b0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
comfy/model_management.py
View File

@ -332,6 +332,7 @@ except:
SUPPORT_FP8_OPS = args.supports_fp8_compute
try:
if is_amd():
torch.backends.cudnn.enabled = False # Seems to improve things a lot on AMD
try:
rocm_version = tuple(map(int, str(torch.version.hip).split(".")[:2]))
except:
@ -925,11 +926,7 @@ def vae_dtype(device=None, allowed_dtypes=[]):
if d == torch.float16 and should_use_fp16(device):
return d
# NOTE: bfloat16 seems to work on AMD for the VAE but is extremely slow in some cases compared to fp32
# slowness still a problem on pytorch nightly 2.9.0.dev20250720+rocm6.4 tested on RDNA3
# also a problem on RDNA4 except fp32 is also slow there.
# This is due to large bf16 convolutions being extremely slow.
if d == torch.bfloat16 and ((not is_amd()) or amd_min_version(device, min_rdna_version=4)) and should_use_bf16(device):
if d == torch.bfloat16 and should_use_bf16(device):
return d
return torch.float32