Skip to content

Commit

Permalink
Remove var in run example
Browse files Browse the repository at this point in the history
  • Loading branch information
jasonacox committed Jun 8, 2024
1 parent 5dbb701 commit 09c70a3
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions vllm/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -105,11 +105,10 @@ nvidia-docker run -d --gpus all -shm-size=10.24gb -p 8000:8000 \
-v $PWD/models:/root/.cache/huggingface \
--env "HF_TOKEN={Your_Hugingface_Token}" \
--restart unless-stopped \
--name $CONTAINER \
--name vllm \
vllm \
--host 0.0.0.0 \
--model=mistralai/Mistral-7B-Instruct-v0.1 \
--served-model-name vllm \
--dtype=float \
--max-model-len 20000

Expand All @@ -120,6 +119,7 @@ nvidia-docker run -d --gpus all -shm-size=10.24gb -p 8000:8000 \
# --disable-log-requests
# --tensor-parallel-size NUM_GPU
# --enforce-eager
# --served-model-name mistral

# Print Running Logs - ^C to Stop Viewing Logs
docker logs vllm -f
Expand Down

0 comments on commit 09c70a3

Please sign in to comment.