1030zero
commented
3 months ago
你好请问这个错误您遇到了么？
Closed CN-COTER closed 2 months ago
1030zero
commented
3 months ago
你好请问这个错误您遇到了么？
CN-COTER
commented
2 months ago
你好请问这个错误您遇到了么？
严格按照这个流程走，我这边现在没有遇到任何问题。
apt-get install git-lfs
git clone https://github.com/Kwai-Kolors/Kolors
cd Kolors
conda create --name kolors python=3.8
conda activate kolors
pip install -r requirements.txt
python3 setup.py install
When execute:
python3 scripts/sample.py "一张瓢虫的照片，微距，变焦，高质量，电影，拿着一个牌子，写着“可图”"Traceback (most recent call last): File "scripts/sample.py", line 42, in
fire.Fire(infer)
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/fire/core.py", line 143, in Fire
component_trace = _Fire(component, args, parsed_flag_args, context, name)
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/fire/core.py", line 477, in _Fire
component, remaining_args = _CallAndUpdateTrace(
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/fire/core.py", line 693, in _CallAndUpdateTrace
component = fn(*varargs, kwargs)
File "scripts/sample.py", line 29, in infer
image = pipe(
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, *kwargs)
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/kolors-0.1-py3.8.egg/kolors/pipelines/pipeline_stable_diffusion_xl_chatglm_256.py", line 714, in call
) = self.encode_prompt(
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/kolors-0.1-py3.8.egg/kolors/pipelines/pipeline_stable_diffusion_xl_chatglm_256.py", line 328, in encode_prompt
output = text_encoder(
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(input, kwargs)
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/accelerate/hooks.py", line 166, in new_forward
output = module._old_forward(*args, kwargs)
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/kolors-0.1-py3.8.egg/kolors/models/modeling_chatglm.py", line 835, in forward
hidden_states, presents, all_hidden_states, all_self_attentions = self.encoder(
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, *kwargs)
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/kolors-0.1-py3.8.egg/kolors/models/modeling_chatglm.py", line 645, in forward
layer_ret = layer(
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(input, kwargs)
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/kolors-0.1-py3.8.egg/kolors/models/modeling_chatglm.py", line 549, in forward
attention_output, kv_cache = self.self_attention(
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, *kwargs)
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/kolors-0.1-py3.8.egg/kolors/models/modeling_chatglm.py", line 446, in forward
context_layer = self.core_attention(query_layer, key_layer, value_layer, attention_mask)
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(input, *kwargs)
File "/root/miniconda3/envs/kolors/lib/python3.8/site-packages/kolors-0.1-py3.8.egg/kolors/models/modeling_chatglm.py", line 259, in forward
matmul_result = torch.baddbmm(
RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling `cublasGemmStridedBatchedExFix( handle, opa, opb, m, n, k, (void)(&falpha), a, CUDA_R_16F, lda, stridea, b, CUDA_R_16F, ldb, strideb, (void*)(&fbeta), c, CUDA_R_16F, ldc, stridec, num_batches, CUDA_R_32F, CUBLAS_GEMM_DEFAULT_TENSOR_OP)`