Comfy UI Crashing at around 40% in.

### Expected Behavior

A character reference sheet matching my source image.

### Actual Behavior

My queue is crashing at about 40% with this error message wasting my initial 30 minute credit. I am wary paying for more credits if this bug keeps recurring. I am new to this and don't understand why it is happening as all my Mac programs are off and the computer is utilizing about 40% memory resources after I initiate the queue prompt to generate a character reference sheet matching my source image.

### Steps to Reproduce

Upload image and select queue prompt.

### Debug Logs

```powershell
# ComfyUI Error Report
## Error Details
- **Node Type:** ApplyPulidFlux
- **Exception Type:** NotImplementedError
- **Exception Message:** No operator found for `memory_efficient_attention_forward` with inputs:
query : shape=(1, 577, 16, 64) (torch.bfloat16)
key : shape=(1, 577, 16, 64) (torch.bfloat16)
value : shape=(1, 577, 16, 64) (torch.bfloat16)
attn_bias :
p : 0.0
`decoderF` is not supported because:
attn_bias type is
bf16 is only supported on A100+ GPUs
`flshattF@2.5.6-pt` is not supported because:
requires device with capability > (8, 0) but your GPU has capability (7, 5) (too old)
bf16 is only supported on A100+ GPUs
`cutlassF-pt` is not supported because:
bf16 is only supported on A100+ GPUs
`smallkF` is not supported because:
max(query.shape[-1] != value.shape[-1]) > 32
dtype=torch.bfloat16 (supported: {torch.float32})
has custom scale
bf16 is only supported on A100+ GPUs
unsupported embed per head: 64
## Stack Trace

File "/data/app/execution.py", line 323, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)

File "/data/app/execution.py", line 198, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)

File "/data/app/execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)

File "/data/app/execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))

File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/pulidflux.py", line 382, in apply_pulid_flux
id_cond_vit, id_vit_hidden = eva_clip(face_features_image, return_all_features=False, return_hidden=True, shuffle=False)

File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)

File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)

File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/eva_clip/eva_vit_model.py", line 544, in forward
x, hidden_states = self.forward_features(x, return_all_features, return_hidden, shuffle)

File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/eva_clip/eva_vit_model.py", line 531, in forward_features
x = blk(x, rel_pos_bias=rel_pos_bias)

File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)

File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)

File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/eva_clip/eva_vit_model.py", line 293, in forward
x = x + self.drop_path(self.attn(self.norm1(x), rel_pos_bias=rel_pos_bias, attn_mask=attn_mask))

File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)

File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)

File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/eva_clip/eva_vit_model.py", line 208, in forward
x = xops.memory_efficient_attention(

File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 276, in memory_efficient_attention
return _memory_efficient_attention(

File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 395, in _memory_efficient_attention
return _memory_efficient_attention_forward(

File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 414, in _memory_efficient_attention_forward
op = _dispatch_fw(inp, False)

File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/dispatch.py", line 119, in _dispatch_fw
return _run_priority_list(

File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/dispatch.py", line 55, in _run_priority_list
raise NotImplementedError(msg)

## System Information
- **ComfyUI Version:** v0.2.6
- **Arguments:** /data/app/main.py --listen --port 30000
- **OS:** posix
- **Python Version:** 3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]
- **Embedded Python:** false
- **PyTorch Version:** 2.4.0+cu121
## Devices

- **Name:** cuda:0 Tesla T4 : cudaMallocAsync
- **Type:** cuda
- **VRAM Total:** 15655829504
- **VRAM Free:** 3733490828
- **Torch VRAM Total:** 12918456320
- **Torch VRAM Free:** 1181650060

## Logs

2025-01-17 08:38:01,466 - root - INFO - Total VRAM 14931 MB, total RAM 15780 MB
2025-01-17 08:38:01,466 - root - INFO - pytorch version: 2.4.0+cu121
2025-01-17 08:38:04,436 - root - INFO - xformers version: 0.0.27.post2
2025-01-17 08:38:04,466 - root - INFO - Set vram state to: NORMAL_VRAM
2025-01-17 08:38:04,466 - root - INFO - Device: cuda:0 Tesla T4 : cudaMallocAsync
2025-01-17 08:38:04,877 - root - INFO - Using xformers cross attention
2025-01-17 08:38:07,529 - root - INFO - [Prompt Server] web root: /data/app/web
2025-01-17 08:38:13,823 - root - INFO - Total VRAM 14931 MB, total RAM 15780 MB
2025-01-17 08:38:13,823 - root - INFO - pytorch version: 2.4.0+cu121
2025-01-17 08:38:13,823 - root - INFO - xformers version: 0.0.27.post2
2025-01-17 08:38:13,823 - root - INFO - Set vram state to: NORMAL_VRAM
2025-01-17 08:38:13,824 - root - INFO - Device: cuda:0 Tesla T4 : cudaMallocAsync
2025-01-17 08:38:29,847 - root - INFO -
Import times for custom nodes:
2025-01-17 08:38:29,847 - root - INFO - 0.1 seconds: /data/app/custom_nodes/cg-use-everywhere
2025-01-17 08:38:29,847 - root - INFO - 0.1 seconds: /data/app/custom_nodes/SD-Latent-Upscaler
2025-01-17 08:38:29,847 - root - INFO - 0.1 seconds: /data/app/custom_nodes/ComfyUI-SAI_API
2025-01-17 08:38:29,847 - root - INFO - 0.3 seconds: /data/app/custom_nodes/ComfyUI-Manager
2025-01-17 08:38:29,847 - root - INFO - 0.4 seconds: /data/app/custom_nodes/ComfyUI_essentials
2025-01-17 08:38:29,847 - root - INFO - 0.5 seconds: /data/app/custom_nodes/ComfyUI-KJNodes
2025-01-17 08:38:29,847 - root - INFO - 0.6 seconds: /data/app/custom_nodes/ComfyUI-Custom-Scripts
2025-01-17 08:38:29,847 - root - INFO - 0.6 seconds: /data/app/custom_nodes/ComfyUI_UltimateSDUpscale
2025-01-17 08:38:29,848 - root - INFO - 0.6 seconds: /data/app/custom_nodes/comfy-image-saver
2025-01-17 08:38:29,848 - root - INFO - 1.5 seconds: /data/app/custom_nodes/ComfyUI-Impact-Pack
2025-01-17 08:38:29,848 - root - INFO - 1.5 seconds: /data/app/custom_nodes/rgthree-comfy
2025-01-17 08:38:29,848 - root - INFO - 2.0 seconds: /data/app/custom_nodes/ComfyUI-AdvancedLivePortrait
2025-01-17 08:38:29,848 - root - INFO - 2.6 seconds: /data/app/custom_nodes/comfyui_controlnet_aux
2025-01-17 08:38:29,848 - root - INFO - 4.1 seconds: /data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced
2025-01-17 08:38:29,848 - root - INFO - 5.3 seconds: /data/app/custom_nodes/was-node-suite-comfyui
2025-01-17 08:38:29,848 - root - INFO -
2025-01-17 08:38:29,902 - root - INFO - Starting server

2025-01-17 08:38:29,903 - root - INFO - To see the GUI go to: http://0.0.0.0:30000
2025-01-17 08:38:29,903 - root - INFO - To see the GUI go to: http://[::]:30000
2025-01-17 08:39:31,595 - root - INFO - got prompt
2025-01-17 08:39:37,208 - root - INFO - Loaded EVA02-CLIP-L-14-336 model config.
2025-01-17 08:39:37,330 - root - INFO - Shape of rope freq: torch.Size([576, 64])
2025-01-17 08:39:43,989 - root - INFO - Loading pretrained EVA02-CLIP-L-14-336 weights (eva_clip).
2025-01-17 08:39:46,870 - root - INFO - incompatible_keys.missing_keys: ['visual.rope.freqs_cos', 'visual.rope.freqs_sin', 'visual.blocks.0.attn.rope.freqs_cos', 'visual.blocks.0.attn.rope.freqs_sin', 'visual.blocks.1.attn.rope.freqs_cos', 'visual.blocks.1.attn.rope.freqs_sin', 'visual.blocks.2.attn.rope.freqs_cos', 'visual.blocks.2.attn.rope.freqs_sin', 'visual.blocks.3.attn.rope.freqs_cos', 'visual.blocks.3.attn.rope.freqs_sin', 'visual.blocks.4.attn.rope.freqs_cos', 'visual.blocks.4.attn.rope.freqs_sin', 'visual.blocks.5.attn.rope.freqs_cos', 'visual.blocks.5.attn.rope.freqs_sin', 'visual.blocks.6.attn.rope.freqs_cos', 'visual.blocks.6.attn.rope.freqs_sin', 'visual.blocks.7.attn.rope.freqs_cos', 'visual.blocks.7.attn.rope.freqs_sin', 'visual.blocks.8.attn.rope.freqs_cos', 'visual.blocks.8.attn.rope.freqs_sin', 'visual.blocks.9.attn.rope.freqs_cos', 'visual.blocks.9.attn.rope.freqs_sin', 'visual.blocks.10.attn.rope.freqs_cos', 'visual.blocks.10.attn.rope.freqs_sin', 'visual.blocks.11.attn.rope.freqs_cos', 'visual.blocks.11.attn.rope.freqs_sin', 'visual.blocks.12.attn.rope.freqs_cos', 'visual.blocks.12.attn.rope.freqs_sin', 'visual.blocks.13.attn.rope.freqs_cos', 'visual.blocks.13.attn.rope.freqs_sin', 'visual.blocks.14.attn.rope.freqs_cos', 'visual.blocks.14.attn.rope.freqs_sin', 'visual.blocks.15.attn.rope.freqs_cos', 'visual.blocks.15.attn.rope.freqs_sin', 'visual.blocks.16.attn.rope.freqs_cos', 'visual.blocks.16.attn.rope.freqs_sin', 'visual.blocks.17.attn.rope.freqs_cos', 'visual.blocks.17.attn.rope.freqs_sin', 'visual.blocks.18.attn.rope.freqs_cos', 'visual.blocks.18.attn.rope.freqs_sin', 'visual.blocks.19.attn.rope.freqs_cos', 'visual.blocks.19.attn.rope.freqs_sin', 'visual.blocks.20.attn.rope.freqs_cos', 'visual.blocks.20.attn.rope.freqs_sin', 'visual.blocks.21.attn.rope.freqs_cos', 'visual.blocks.21.attn.rope.freqs_sin', 'visual.blocks.22.attn.rope.freqs_cos', 'visual.blocks.22.attn.rope.freqs_sin', 'visual.blocks.23.attn.rope.freqs_cos', 'visual.blocks.23.attn.rope.freqs_sin']
2025-01-17 08:39:51,243 - root - INFO - Loading PuLID-Flux model.
2025-01-17 08:39:56,308 - root - INFO - Using xformers attention in VAE
2025-01-17 08:39:56,310 - root - INFO - Using xformers attention in VAE
2025-01-17 08:39:56,861 - root - WARNING - Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.
2025-01-17 08:39:58,923 - root - INFO - Requested to load FluxClipModel_
2025-01-17 08:39:58,924 - root - INFO - Loading 1 new model
2025-01-17 08:39:58,936 - root - INFO - loaded completely 0.0 9319.23095703125 True
2025-01-17 08:39:59,461 - root - WARNING - clip missing: ['text_projection.weight']
2025-01-17 08:40:23,662 - root - INFO - model weight dtype torch.float8_e4m3fn, manual cast: torch.float16
2025-01-17 08:40:23,669 - root - INFO - model_type FLUX
2025-01-17 08:42:23,180 - root - ERROR - !!! Exception during processing !!! No operator found for `memory_efficient_attention_forward` with inputs:
query : shape=(1, 577, 16, 64) (torch.bfloat16)
key : shape=(1, 577, 16, 64) (torch.bfloat16)
value : shape=(1, 577, 16, 64) (torch.bfloat16)
attn_bias :
p : 0.0
`decoderF` is not supported because:
attn_bias type is
bf16 is only supported on A100+ GPUs
`flshattF@2.5.6-pt` is not supported because:
requires device with capability > (8, 0) but your GPU has capability (7, 5) (too old)
bf16 is only supported on A100+ GPUs
`cutlassF-pt` is not supported because:
bf16 is only supported on A100+ GPUs
`smallkF` is not supported because:
max(query.shape[-1] != value.shape[-1]) > 32
dtype=torch.bfloat16 (supported: {torch.float32})
has custom scale
bf16 is only supported on A100+ GPUs
unsupported embed per head: 64
2025-01-17 08:42:23,357 - root - ERROR - Traceback (most recent call last):
File "/data/app/execution.py", line 323, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
File "/data/app/execution.py", line 198, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
File "/data/app/execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)
File "/data/app/execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))
File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/pulidflux.py", line 382, in apply_pulid_flux
id_cond_vit, id_vit_hidden = eva_clip(face_features_image, return_all_features=False, return_hidden=True, shuffle=False)
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/eva_clip/eva_vit_model.py", line 544, in forward
x, hidden_states = self.forward_features(x, return_all_features, return_hidden, shuffle)
File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/eva_clip/eva_vit_model.py", line 531, in forward_features
x = blk(x, rel_pos_bias=rel_pos_bias)
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/eva_clip/eva_vit_model.py", line 293, in forward
x = x + self.drop_path(self.attn(self.norm1(x), rel_pos_bias=rel_pos_bias, attn_mask=attn_mask))
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/eva_clip/eva_vit_model.py", line 208, in forward
x = xops.memory_efficient_attention(
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 276, in memory_efficient_attention
return _memory_efficient_attention(
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 395, in _memory_efficient_attention
return _memory_efficient_attention_forward(
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 414, in _memory_efficient_attention_forward
op = _dispatch_fw(inp, False)
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/dispatch.py", line 119, in _dispatch_fw
return _run_priority_list(
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/dispatch.py", line 55, in _run_priority_list
raise NotImplementedError(msg)
NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs:
query : shape=(1, 577, 16, 64) (torch.bfloat16)
key : shape=(1, 577, 16, 64) (torch.bfloat16)
value : shape=(1, 577, 16, 64) (torch.bfloat16)
attn_bias :
p : 0.0
`decoderF` is not supported because:
attn_bias type is
bf16 is only supported on A100+ GPUs
`flshattF@2.5.6-pt` is not supported because:
requires device with capability > (8, 0) but your GPU has capability (7, 5) (too old)
bf16 is only supported on A100+ GPUs
`cutlassF-pt` is not supported because:
bf16 is only supported on A100+ GPUs
`smallkF` is not supported because:
max(query.shape[-1] != value.shape[-1]) > 32
dtype=torch.bfloat16 (supported: {torch.float32})
has custom scale
bf16 is only supported on A100+ GPUs
unsupported embed per head: 64

2025-01-17 08:42:23,436 - root - INFO - Prompt executed in 171.77 seconds
2025-01-17 08:43:16,175 - root - INFO - got prompt
2025-01-17 08:43:20,382 - root - ERROR - !!! Exception during processing !!! No operator found for `memory_efficient_attention_forward` with inputs:
query : shape=(1, 577, 16, 64) (torch.bfloat16)
key : shape=(1, 577, 16, 64) (torch.bfloat16)
value : shape=(1, 577, 16, 64) (torch.bfloat16)
attn_bias :
p : 0.0
`decoderF` is not supported because:
attn_bias type is
bf16 is only supported on A100+ GPUs
`flshattF@2.5.6-pt` is not supported because:
requires device with capability > (8, 0) but your GPU has capability (7, 5) (too old)
bf16 is only supported on A100+ GPUs
`cutlassF-pt` is not supported because:
bf16 is only supported on A100+ GPUs
`smallkF` is not supported because:
max(query.shape[-1] != value.shape[-1]) > 32
dtype=torch.bfloat16 (supported: {torch.float32})
has custom scale
bf16 is only supported on A100+ GPUs
unsupported embed per head: 64
2025-01-17 08:43:20,463 - root - ERROR - Traceback (most recent call last):
File "/data/app/execution.py", line 323, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
File "/data/app/execution.py", line 198, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
File "/data/app/execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)
File "/data/app/execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))
File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/pulidflux.py", line 382, in apply_pulid_flux
id_cond_vit, id_vit_hidden = eva_clip(face_features_image, return_all_features=False, return_hidden=True, shuffle=False)
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/eva_clip/eva_vit_model.py", line 544, in forward
x, hidden_states = self.forward_features(x, return_all_features, return_hidden, shuffle)
File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/eva_clip/eva_vit_model.py", line 531, in forward_features
x = blk(x, rel_pos_bias=rel_pos_bias)
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/eva_clip/eva_vit_model.py", line 293, in forward
x = x + self.drop_path(self.attn(self.norm1(x), rel_pos_bias=rel_pos_bias, attn_mask=attn_mask))
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/data/app/custom_nodes/ComfyUI-PuLID-Flux-Enhanced/eva_clip/eva_vit_model.py", line 208, in forward
x = xops.memory_efficient_attention(
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 276, in memory_efficient_attention
return _memory_efficient_attention(
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 395, in _memory_efficient_attention
return _memory_efficient_attention_forward(
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 414, in _memory_efficient_attention_forward
op = _dispatch_fw(inp, False)
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/dispatch.py", line 119, in _dispatch_fw
return _run_priority_list(
File "/data/miniconda3/pkgs/comfyui/lib/python3.10/site-packages/xformers/ops/fmha/dispatch.py", line 55, in _run_priority_list
raise NotImplementedError(msg)
NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs:
query : shape=(1, 577, 16, 64) (torch.bfloat16)
key : shape=(1, 577, 16, 64) (torch.bfloat16)
value : shape=(1, 577, 16, 64) (torch.bfloat16)
attn_bias :
p : 0.0
`decoderF` is not supported because:
attn_bias type is
bf16 is only supported on A100+ GPUs
`flshattF@2.5.6-pt` is not supported because:
requires device with capability > (8, 0) but your GPU has capability (7, 5) (too old)
bf16 is only supported on A100+ GPUs
`cutlassF-pt` is not supported because:
bf16 is only supported on A100+ GPUs
`smallkF` is not supported because:
max(query.shape[-1] != value.shape[-1]) > 32
dtype=torch.bfloat16 (supported: {torch.float32})
has custom scale
bf16 is only supported on A100+ GPUs
unsupported embed per head: 64

2025-01-17 08:43:20,464 - root - INFO - Prompt executed in 4.23 seconds

## Attached Workflow
Please make sure that workflow does not contain any sensitive information such as API keys or passwords.

Workflow too large. Please manually upload the workflow from local file system.

## Additional Context
(Please add any additional context or steps to reproduce the error here)
```

### Other

_No response_