runtime error
β β 283 β β β β attention_mask = None β β 284 β β β β β 285 β β β prompt_embeds = self.text_encoder( β β β± 286 β β β β text_input_ids.to(device), β β 287 β β β β attention_mask=attention_mask, β β 288 β β β ) β β 289 β β β prompt_embeds = prompt_embeds[0] β β β β /usr/local/lib/python3.10/site-packages/torch/cuda/__init__.py:247 in β β _lazy_init β β β β 244 β β # are found or any other error occurs β β 245 β β if 'CUDA_MODULE_LOADING' not in os.environ: β β 246 β β β os.environ['CUDA_MODULE_LOADING'] = 'LAZY' β β β± 247 β β torch._C._cuda_init() β β 248 β β # Some of the queued calls may reentrantly call _lazy_init(); β β 249 β β # we need to just return without initializing in that case. β β 250 β β # However, we must not let any *other* threads in! β β°βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ― RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx
Container logs:
Fetching error logs...