mirror of https://github.com/vllm-project/vllm
17 lines
531 B
Bash
17 lines
531 B
Bash
set -e
|
|
|
|
# Build the docker image.
|
|
docker build -f Dockerfile.tpu -t vllm-tpu .
|
|
|
|
# Set up cleanup.
|
|
remove_docker_container() { docker rm -f tpu-test || true; }
|
|
trap remove_docker_container EXIT
|
|
# Remove the container that might not be cleaned up in the previous run.
|
|
remove_docker_container
|
|
|
|
# For HF_TOKEN.
|
|
source /etc/environment
|
|
# Run a simple end-to-end example.
|
|
docker run --privileged --net host --shm-size=16G -it -e HF_TOKEN=$HF_TOKEN --name tpu-test vllm-tpu \
|
|
python3 /workspace/vllm/examples/offline_inference_tpu.py
|