Colab Error – xFormers wasn't build with CUDA support

[lucalopez]

If i try to run the colab version im getting this error - does someone know a solution:

Traceback (most recent call last):
File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/usr/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/content/Fooocus-MRE/modules/async_worker.py", line 613, in worker
handler(task)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/content/Fooocus-MRE/modules/async_worker.py", line 487, in handler
imgs = pipeline.process_diffusion(
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/content/Fooocus-MRE/modules/default_pipeline.py", line 403, in process_diffusion
sampled_latent = core.ksampler(
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/content/Fooocus-MRE/modules/core.py", line 347, in ksampler
samples = sampler.sample(noise, positive_copy, negative_copy, cfg=cfg, latent_image=latent_image,
File "/content/Fooocus-MRE/modules/samplers_advanced.py", line 202, in sample
samples = getattr(k_diffusion_sampling, "sample{}".format(self.sampler))(self.model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/content/Fooocus-MRE/repositories/ComfyUI-from-StabilityAI-Official/comfy/k_diffusion/sampling.py", line 701, in sample_dpmpp_2m_sde_gpu
return sample_dpmpp_2m_sde(model, x, sigmas, extra_args=extra_args, callback=callback, disable=disable, eta=eta, s_noise=s_noise, noise_sampler=noise_sampler, solver_type=solver_type)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/content/Fooocus-MRE/repositories/ComfyUI-from-StabilityAI-Official/comfy/k_diffusion/sampling.py", line 613, in sample_dpmpp_2m_sde
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/content/Fooocus-MRE/repositories/ComfyUI-from-StabilityAI-Official/comfy/samplers.py", line 323, in forward
out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, cond_concat=cond_concat, model_options=model_options, seed=seed)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in call_impl
return forward_call(*args, **kwargs)
File "/content/Fooocus-MRE/modules/patch.py", line 164, in patched_discrete_eps_ddpm_denoiser_forward
return self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
File "/content/Fooocus-MRE/repositories/ComfyUI-from-StabilityAI-Official/comfy/k_diffusion/external.py", line 151, in get_eps
return self.inner_model.apply_model(*args, **kwargs)
File "/content/Fooocus-MRE/repositories/ComfyUI-from-StabilityAI-Official/comfy/samplers.py", line 311, in apply_model
out = sampling_function(self.inner_model.apply_model, x, timestep, uncond, cond, cond_scale, cond_concat, model_options=model_options, seed=seed)
File "/content/Fooocus-MRE/repositories/ComfyUI-from-StabilityAI-Official/comfy/samplers.py", line 289, in sampling_function
cond, uncond = calc_cond_uncond_batch(model_function, cond, uncond, x, timestep, max_total_area, cond_concat, model_options)
File "/content/Fooocus-MRE/repositories/ComfyUI-from-StabilityAI-Official/comfy/samplers.py", line 263, in calc_cond_uncond_batch
output = model_options['model_function_wrapper'](model_function, {"input": input_x, "timestep": timestep, "c": c, "cond_or_uncond": cond_or_uncond}).chunk(batch_chunks)
File "/content/Fooocus-MRE/modules/patch.py", line 173, in patched_model_function
return func(x, t, **c)
File "/content/Fooocus-MRE/repositories/ComfyUI-from-StabilityAI-Official/comfy/model_base.py", line 63, in apply_model
return self.diffusion_model(xc, t, context=context, y=c_adm, control=control, transformer_options=transformer_options).float()
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/content/Fooocus-MRE/modules/patch.py", line 338, in patched_unet_forward
h = forward_timestep_embed(module, h, emb, context, transformer_options)
File "/content/Fooocus-MRE/repositories/ComfyUI-from-StabilityAI-Official/comfy/ldm/modules/diffusionmodules/openaimodel.py", line 56, in forward_timestep_embed
x = layer(x, context, transformer_options)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/content/Fooocus-MRE/repositories/ComfyUI-from-StabilityAI-Official/comfy/ldm/modules/attention.py", line 693, in forward
x = block(x, context=context[i], transformer_options=transformer_options)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/content/Fooocus-MRE/repositories/ComfyUI-from-StabilityAI-Official/comfy/ldm/modules/attention.py", line 525, in forward
return checkpoint(self._forward, (x, context, transformer_options), self.parameters(), self.checkpoint)
File "/content/Fooocus-MRE/repositories/ComfyUI-from-StabilityAI-Official/comfy/ldm/modules/diffusionmodules/util.py", line 123, in checkpoint
return func(*inputs)
File "/content/Fooocus-MRE/repositories/ComfyUI-from-StabilityAI-Official/comfy/ldm/modules/attention.py", line 588, in _forward
n = self.attn1(n, context=context_attn1, value=value_attn1)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/content/Fooocus-MRE/repositories/ComfyUI-from-StabilityAI-Official/comfy/ldm/modules/attention.py", line 438, in forward
out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None, op=self.attention_op)
File "/usr/local/lib/python3.10/dist-packages/xformers/ops/fmha/init.py", line 193, in memory_efficient_attention
return _memory_efficient_attention(
File "/usr/local/lib/python3.10/dist-packages/xformers/ops/fmha/init.py", line 291, in _memory_efficient_attention
return _memory_efficient_attention_forward(
File "/usr/local/lib/python3.10/dist-packages/xformers/ops/fmha/init.py", line 307, in _memory_efficient_attention_forward
op = _dispatch_fw(inp, False)
File "/usr/local/lib/python3.10/dist-packages/xformers/ops/fmha/dispatch.py", line 96, in _dispatch_fw
return _run_priority_list(
File "/usr/local/lib/python3.10/dist-packages/xformers/ops/fmha/dispatch.py", line 63, in _run_priority_list
raise NotImplementedError(msg)
NotImplementedError: No operator found for memory_efficient_attention_forward with inputs:
query : shape=(20, 4032, 1, 64) (torch.float16)
key : shape=(20, 4032, 1, 64) (torch.float16)
value : shape=(20, 4032, 1, 64) (torch.float16)
attn_bias : <class 'NoneType'>
p : 0.0
decoderF is not supported because:
xFormers wasn't build with CUDA support
requires device with capability > (8, 0) but your GPU has capability (7, 5) (too old)
attn_bias type is <class 'NoneType'>
operator wasn't built - see python -m xformers.info for more info
[email protected] is not supported because:
xFormers wasn't build with CUDA support
requires device with capability > (8, 0) but your GPU has capability (7, 5) (too old)
operator wasn't built - see python -m xformers.info for more info
tritonflashattF is not supported because:
xFormers wasn't build with CUDA support
requires device with capability > (8, 0) but your GPU has capability (7, 5) (too old)
operator wasn't built - see python -m xformers.info for more info
triton is not available
requires GPU with sm80 minimum compute capacity, e.g., A100/H100/L4
Only work on pre-MLIR triton for now
cutlassF is not supported because:
xFormers wasn't build with CUDA support
operator wasn't built - see python -m xformers.info for more info
smallkF is not supported because:
max(query.shape[-1] != value.shape[-1]) > 32
xFormers wasn't build with CUDA support
dtype=torch.float16 (supported: {torch.float32})
operator wasn't built - see python -m xformers.info for more info
unsupported embed per head: 64