Error RuntimeError: CUDA error: misaligned address CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

[busminer]

Hello, can you please help always getting this error on windows

RuntimeError: CUDA error: misaligned address
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

[busminer]

[Fooocus Model Management] Moving model(s) has taken 8.87 seconds
77%|██████████████████████████████████████████████████████████████▊ | 23/30 [02:20<00:42, 6.10s/it]
Traceback (most recent call last):
File "G:\Fooocus_win64_2-1-831\Fooocus\modules\async_worker.py", line 822, in worker
handler(task)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\modules\async_worker.py", line 753, in handler
imgs = pipeline.process_diffusion(
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\modules\default_pipeline.py", line 361, in process_diffusion
sampled_latent = core.ksampler(
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\modules\core.py", line 313, in ksampler
samples = ldm_patched.modules.sample.sample(model,
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\modules\sample.py", line 100, in sample
samples = sampler.sample(noise, positive_copy, negative_copy, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\modules\samplers.py", line 712, in sample
return sample(self.model, noise, positive, negative, cfg, self.device, sampler, sigmas, self.model_options, latent_image=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\modules\sample_hijack.py", line 157, in sample_hacked
samples = sampler.sample(model_wrap, sigmas, extra_args, callback_wrap, noise, latent_image, denoise_mask, disable_pbar)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\modules\samplers.py", line 557, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\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 "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\k_diffusion\sampling.py", line 613, in sample_dpmpp_2m_sde
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\modules\patch.py", line 314, in patched_KSamplerX0Inpaint_forward
out = self.inner_model(x, sigma,
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1527, in call_impl
return forward_call(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\modules\samplers.py", line 271, in forward
return self.apply_model(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\modules\samplers.py", line 268, in apply_model
out = sampling_function(self.inner_model, x, timestep, uncond, cond, cond_scale, model_options=model_options, seed=seed)
File "G:\Fooocus_win64_2-1-831\Fooocus\modules\patch.py", line 229, in patched_sampling_function
positive_x0, negative_x0 = calc_cond_uncond_batch(model, cond, uncond, x, timestep, model_options)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\modules\samplers.py", line 222, in calc_cond_uncond_batch
output = model.apply_model(input_x, timestep, **c).chunk(batch_chunks)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\modules\model_base.py", line 85, in apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\modules\patch.py", line 431, in patched_unet_forward
h = forward_timestep_embed(module, h, emb, context, transformer_options, output_shape, time_context=time_context, num_video_frames=num_video_frames, image_only_indicator=image_only_indicator)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\ldm\modules\diffusionmodules\openaimodel.py", line 43, in forward_timestep_embed
x = layer(x, context, transformer_options)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\ldm\modules\attention.py", line 613, in forward
x = block(x, context=context[i], transformer_options=transformer_options)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\ldm\modules\attention.py", line 440, in forward
return checkpoint(self._forward, (x, context, transformer_options), self.parameters(), self.checkpoint)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\ldm\modules\diffusionmodules\util.py", line 189, in checkpoint
return func(*inputs)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\ldm\modules\attention.py", line 540, in _forward
n = self.attn2(n, context=context_attn2, value=value_attn2)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\ldm\modules\attention.py", line 382, in forward
q = self.to_q(x)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\modules\ops.py", line 25, in forward
return self.forward_ldm_patched_cast_weights(*args, **kwargs)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\modules\ops.py", line 20, in forward_ldm_patched_cast_weights
weight, bias = cast_bias_weight(self, input)
File "G:\Fooocus_win64_2-1-831\Fooocus\ldm_patched\modules\ops.py", line 9, in cast_bias_weight
weight = s.weight.to(device=input.device, dtype=input.dtype, non_blocking=non_blocking)
RuntimeError: CUDA error: misaligned address
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

Total time: 174.57 seconds