Skip to content

GitLab

Commit 0966d3ce authored by comfyanonymous's avatar comfyanonymous
Browse files

Don't run text encoders on xpu because there are issues.

parent 0e4395a8
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
comfy/model_management.py
View file @ 0966d3ce
...@@ -451,6 +451,8 @@ def text_encoder_device(): ...@@ -451,6 +451,8 @@ def text_encoder_device():
if args.gpu_only: if args.gpu_only:
return get_torch_device() return get_torch_device()
elif vram_state == VRAMState.HIGH_VRAM or vram_state == VRAMState.NORMAL_VRAM: elif vram_state == VRAMState.HIGH_VRAM or vram_state == VRAMState.NORMAL_VRAM:
if is_intel_xpu():
return torch.device("cpu")
if should_use_fp16(prioritize_performance=False): if should_use_fp16(prioritize_performance=False):
return get_torch_device() return get_torch_device()
else: else:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment