I run it in a server with Tesla M40.
In loadding model,it's show
Getting T5 embs...
Traceback (most recent call last):
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/gradio/routes.py", line 437, in run_predict
output = await app.get_blocks().process_api(
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/gradio/blocks.py", line 1352, in process_api
result = await self.call_function(
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/gradio/blocks.py", line 1077, in call_function
prediction = await anyio.to_thread.run_sync(
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/anyio/to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 807, in run
result = context.run(func, *args)
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/gradio/helpers.py", line 602, in tracked_fn
response = fn(*args)
File "/media/maoweicao/DATA1/IF-webui/webui.py", line 208, in generate_images
result = dream(
File "/media/maoweicao/DATA1/IF-webui/deepfloyd_if/pipelines/dream.py", line 64, in dream
t5_embs = t5.get_text_embeddings(prompt)
File "/media/maoweicao/DATA1/IF-webui/deepfloyd_if/modules/t5.py", line 96, in get_text_embeddings
text_encoder_embs = self.model(
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/accelerate/hooks.py", line 156, in new_forward
output = old_forward(*args, **kwargs)
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/transformers/models/t5/modeling_t5.py", line 1846, in forward
encoder_outputs = self.encoder(
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/transformers/models/t5/modeling_t5.py", line 1040, in forward
layer_outputs = layer_module(
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/accelerate/hooks.py", line 156, in new_forward
output = old_forward(*args, **kwargs)
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/transformers/models/t5/modeling_t5.py", line 673, in forward
self_attention_outputs = self.layer[0](
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/accelerate/hooks.py", line 156, in new_forward
output = old_forward(*args, **kwargs)
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/transformers/models/t5/modeling_t5.py", line 579, in forward
attention_output = self.SelfAttention(
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/accelerate/hooks.py", line 156, in new_forward
output = old_forward(*args, **kwargs)
File "/home/maoweicao/miniconda3/envs/if-webui/lib/python3.10/site-packages/transformers/models/t5/modeling_t5.py", line 509, in forward
scores = torch.matmul(
RuntimeError: CUDA error: CUBLAS_STATUS_NOT_SUPPORTED when calling cublasGemmStridedBatchedExFix(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, CUDA_R_32F, CUBLAS_GEMM_DEFAULT_TENSOR_OP)