worker-vllm build fails
I am getting the following error when building the new worker-vllm image with my model.
=> ERROR [vllm-base 6/7] RUN --mount=type=secret,id=HF_TOKEN,required=false if [ -f /run/secrets/HF_TOKEN ]; then export HF_TOKEN=$(cat /run/secrets/HF_TOKEN); fi && if [ -n "Pate 10.5s
------
> [vllm-base 6/7] RUN --mount=type=secret,id=HF_TOKEN,required=false if [ -f /run/secrets/HF_TOKEN ]; then export HF_TOKEN=$(cat /run/secrets/HF_TOKEN); fi && if [ -n "PatentPilotAI/mistral-7b-patent-instruct-v2" ]; then python3 /download_model.py; fi:
#10 9.713 Traceback (most recent call last):
#10 9.713 File "/download_model.py", line 4, in <module>
#10 9.715 from vllm.model_executor.weight_utils import prepare_hf_model_weights, Disabledtqdm
#10 9.715 File "/vllm-installation/vllm/model_executor/__init__.py", line 2, in <module>
#10 9.715 from vllm.model_executor.model_loader import get_model
#10 9.715 File "/vllm-installation/vllm/model_executor/model_loader.py", line 10, in <module>
#10 9.715 from vllm.model_executor.weight_utils import (get_quant_config,
#10 9.715 File "/vllm-installation/vllm/model_executor/weight_utils.py", line 18, in <module>
#10 9.715 from vllm.model_executor.layers.quantization import (get_quantization_config,
#10 9.715 File "/vllm-installation/vllm/model_executor/layers/quantization/__init__.py", line 4, in <module>
#10 9.716 from vllm.model_executor.layers.quantization.awq import AWQConfig
#10 9.716 File "/vllm-installation/vllm/model_executor/layers/quantization/awq.py", line 6, in <module>
#10 9.716 from vllm._C import ops
#10 9.716 ImportError: libcuda.so.1: cannot open shared object file: No such file or directory => ERROR [vllm-base 6/7] RUN --mount=type=secret,id=HF_TOKEN,required=false if [ -f /run/secrets/HF_TOKEN ]; then export HF_TOKEN=$(cat /run/secrets/HF_TOKEN); fi && if [ -n "Pate 10.5s
------
> [vllm-base 6/7] RUN --mount=type=secret,id=HF_TOKEN,required=false if [ -f /run/secrets/HF_TOKEN ]; then export HF_TOKEN=$(cat /run/secrets/HF_TOKEN); fi && if [ -n "PatentPilotAI/mistral-7b-patent-instruct-v2" ]; then python3 /download_model.py; fi:
#10 9.713 Traceback (most recent call last):
#10 9.713 File "/download_model.py", line 4, in <module>
#10 9.715 from vllm.model_executor.weight_utils import prepare_hf_model_weights, Disabledtqdm
#10 9.715 File "/vllm-installation/vllm/model_executor/__init__.py", line 2, in <module>
#10 9.715 from vllm.model_executor.model_loader import get_model
#10 9.715 File "/vllm-installation/vllm/model_executor/model_loader.py", line 10, in <module>
#10 9.715 from vllm.model_executor.weight_utils import (get_quant_config,
#10 9.715 File "/vllm-installation/vllm/model_executor/weight_utils.py", line 18, in <module>
#10 9.715 from vllm.model_executor.layers.quantization import (get_quantization_config,
#10 9.715 File "/vllm-installation/vllm/model_executor/layers/quantization/__init__.py", line 4, in <module>
#10 9.716 from vllm.model_executor.layers.quantization.awq import AWQConfig
#10 9.716 File "/vllm-installation/vllm/model_executor/layers/quantization/awq.py", line 6, in <module>
#10 9.716 from vllm._C import ops
#10 9.716 ImportError: libcuda.so.1: cannot open shared object file: No such file or directory
