Error when loading a model after latest commits

Nobody has claimed this yet.

Moving model(s) has taken 9.44 seconds
0%| | 0/10 [00:01
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "D:\webui_forge_cu121_torch231\system\python\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\webui_forge_cu121_torch231\webui\k_diffusion\sampling.py", line 594, in sample_dpmpp_2m
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "D:\webui_forge_cu121_torch231\system\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\webui_forge_cu121_torch231\system\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "D:\webui_forge_cu121_torch231\webui\modules\sd_samplers_cfg_denoiser.py", line 186, in forward
denoised, cond_pred, uncond_pred = sampling_function(self, denoiser_params=denoiser_params, cond_scale=cond_scale, cond_composition=cond_composition)
File "D:\webui_forge_cu121_torch231\webui\backend\sampling\sampling_function.py", line 339, in sampling_function
denoised, cond_pred, uncond_pred = sampling_function_inner(model, x, timestep, uncond, cond, cond_scale, model_options, seed, return_full=True)
File "D:\webui_forge_cu121_torch231\webui\backend\sampling\sampling_function.py", line 284, in sampling_function_inner
cond_pred, uncond_pred = calc_cond_uncond_batch(model, cond, uncond_, x, timestep, model_options)
File "D:\webui_forge_cu121_torch231\webui\backend\sampling\sampling_function.py", line 254, in calc_cond_uncond_batch
output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
File "D:\webui_forge_cu121_torch231\webui\backend\modules\k_model.py", line 45, in apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
File "D:\webui_forge_cu121_torch231\system\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\webui_forge_cu121_torch231\system\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "D:\webui_forge_cu121_torch231\webui\backend\nn\unet.py", line 713, in forward
h = module(h, emb, context, transformer_options)
File "D:\webui_forge_cu121_torch231\system\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\webui_forge_cu121_torch231\system\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "D:\webui_forge_cu121_torch231\webui\backend\nn\unet.py", line 83, in forward
x = layer(x, context, transformer_options)
File "D:\webui_forge_cu121_torch231\system\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\webui_forge_cu121_torch231\system\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "D:\webui_forge_cu121_torch231\webui\backend\nn\unet.py", line 321, in forward
x = block(x, context=context[i], transformer_options=transformer_options)
File "D:\webui_forge_cu121_torch231\system\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\webui_forge_cu121_torch231\system\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "D:\webui_forge_cu121_torch231\webui\backend\nn\unet.py", line 181, in forward
return checkpoint(self._forward, (x, context, transformer_options), None, self.checkpoint)
File "D:\webui_forge_cu121_torch231\webui\backend\nn\unet.py", line 12, in checkpoint
return f(*args)
File "D:\webui_forge_cu121_torch231\webui\backend\nn\unet.py", line 235, in _forward
n = self.attn1(n, context=context_attn1, value=value_attn1, transformer_options=extra_options)
File "D:\webui_forge_cu121_torch231\system\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\webui_forge_cu121_torch231\system\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "D:\webui_forge_cu121_torch231\webui\backend\nn\unet.py", line 154, in forward
out = attention_function(q, k, v, self.heads, mask)
File "D:\webui_forge_cu121_torch231\webui\backend\attention.py", line 345, in attention_pytorch
out = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False)
RuntimeError: CUDA error: CUBLAS_STATUS_NOT_SUPPORTED when calling `cublasGemmStridedBatchedEx(handle, opa, opb, (int)m, (int)n, (int)k, (void*)&falpha, a, CUDA_R_16BF, (int)lda, stridea, b, CUDA_R_16BF, (int)ldb, strideb, (void*)&fbeta, c, CUDA_R_16BF, (int)ldc, stridec, (int)num_batches, compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP)`
CUDA error: CUBLAS_STATUS_NOT_SUPPORTED when calling `cublasGemmStridedBatchedEx(handle, opa, opb, (int)m, (int)n, (int)k, (void*)&falpha, a, CUDA_R_16BF, (int)lda, stridea, b, CUDA_R_16BF, (int)ldb, strideb, (void*)&fbeta, c, CUDA_R_16BF, (int)ldc, stridec, (int)num_batches, compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP)`
*** Error completing request
*** Arguments: ('task(9jxtq5t95hpu5ut)', , 'cat', '', [], 1, 1, 5, 0, 1152, 896, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', 'Use same scheduler', '', '', None, 0, 10, 'DPM++ 2M', 'Karras', False, -1, False, -1, 0, 0, 0, False, 7, 1, 'Constant', 0, 'Constant', 0, 1, 'enable', 'MEAN', 'AD', 1, False, 0, 'anisotropic', 0, 'reinhard', 100, 0, 'subtract', 0, 0, 'gaussian', 'add', 0, 100, 127, 0, 'hard_clamp', 5, 0, 'None', 'None', False, 'MultiDiffusion', 768, 768, 64, 4, False, True, False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '', '', 0, '', '', 0, '', '', True, False, False, False, False, False, False, 0, False) {}
Traceback (most recent call last):
File "D:\webui_forge_cu121_torch231\webui\modules\call_queue.py", line 74, in f
res = list(func(*args, **kwargs))
TypeError: 'NoneType' object is not iterable

Start at backend/attention.py in attention_pytorch, then trace the failing call through backend/nn/unet.py and the listed sampling entry points. Reproduce the txt2img request with the shown DPM++ 2M settings and CUDA error, including the follow-on NoneType failure. Done means the model loads and the request completes without either error.

Written by the indexing model from the issue text.