xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-15 01:45:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add support for multi-node on CI (#5955)

Browse Source 
Signed-off-by: kevin <kevin@anyscale.com>
This commit is contained in:
Kevin H. Luu 2024-07-09 12:56:56 -07:00 committed by GitHub
parent 08c5bdecae
commit a0550cbc80
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 77 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

77
.buildkite/run-multi-node-test.sh Executable file
View File

@ -0,0 +1,77 @@
#!/bin/bash
set -euox pipefail
if [[ $# -lt 3 ]]; then
echo "Please provide the number of nodes and GPU per node."
exit 1
fi
NUM_NODES=$1
NUM_GPUS=$2
DOCKER_IMAGE=$3
shift 3
COMMANDS=("$@")
if [ ${#COMMANDS[@]} -ne $NUM_NODES ]; then
echo "The number of commands must be equal to the number of nodes."
echo "Number of nodes: $NUM_NODES"
echo "Number of commands: ${#COMMANDS[@]}"
exit 1
fi
echo "List of commands"
for command in "${COMMANDS[@]}"; do
echo $command
done
start_network() {
docker network create --subnet=192.168.10.0/24 docker-net
}
start_nodes() {
for node in $(seq 0 $(($NUM_NODES-1))); do
GPU_DEVICES='"device='
for node_gpu in $(seq 0 $(($NUM_GPUS - 1))); do
DEVICE_NUM=$(($node * $NUM_GPUS + $node_gpu))
GPU_DEVICES+=$(($DEVICE_NUM))
if [ $node_gpu -lt $(($NUM_GPUS - 1)) ]; then
GPU_DEVICES+=','
fi
done
GPU_DEVICES+='"'
# echo "Starting node$node with GPU devices: $GPU_DEVICES"
docker run -d --gpus "$GPU_DEVICES" --name node$node --network docker-net --ip 192.168.10.$((10 + $node)) --rm $DOCKER_IMAGE tail -f /dev/null
done
}
run_nodes() {
for node in $(seq 0 $(($NUM_NODES-1))); do
GPU_DEVICES='"device='
for node_gpu in $(seq 0 $(($NUM_GPUS - 1))); do
DEVICE_NUM=$(($node * $NUM_GPUS + $node_gpu))
GPU_DEVICES+=$(($DEVICE_NUM))
if [ $node_gpu -lt $(($NUM_GPUS - 1)) ]; then
GPU_DEVICES+=','
fi
done
GPU_DEVICES+='"'
echo "Running node$node with GPU devices: $GPU_DEVICES"
if [ $node -lt $(($NUM_NODES - 1)) ]; then
docker exec -d node$node /bin/bash -c "${COMMANDS[$node]}"
else
docker exec node$node /bin/bash -c "${COMMANDS[$node]}"
fi
done
}
cleanup() {
for node in $(seq 0 $(($NUM_NODES-1))); do
docker stop node$node
done
docker network rm docker-net
}
trap cleanup EXIT
start_network
start_nodes
run_nodes