dgx-spark-playbooks/nvidia/txt2kg/assets/deploy/services/vllm/run_container.sh

mirror of https://github.com/NVIDIA/dgx-spark-playbooks.git synced 2026-04-26 11:53:53 +00:00
#!/bin/bash

# Follow the official vLLM tutorial run_container.sh exactly
docker run -e HF_TOKEN="$HF_TOKEN" -e HF_HOME="$HF_HOME" --ipc=host --gpus all --entrypoint "/bin/bash" --rm -it vllm/vllm-openai:deploy
chore: Regenerate all playbooks 2025-10-06 17:05:41 +00:00			`#!/bin/bash`

			`# Follow the official vLLM tutorial run_container.sh exactly`
			`docker run -e HF_TOKEN="$HF_TOKEN" -e HF_HOME="$HF_HOME" --ipc=host --gpus all --entrypoint "/bin/bash" --rm -it vllm/vllm-openai:deploy`