software-engineering/spark-vllm-docker
2
0
Fork 0
Code Issues Actions Packages Projects Releases Wiki Activity

Added ability to launch NGC container in the cluster

Browse Source
This commit is contained in:
Eugene Rakhmatulin
2026-02-02 16:57:04 -08:00
parent 4634ee92a2
commit 4b9ab0de7c
5 changed files with 162 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
launch-cluster.sh
View File

@@ -403,14 +403,15 @@ apply_mod_to_container() {
# 3. Run run.sh
echo " Running patch script on $node_ip..."
local exec_cmd="cd $container_dest && chmod +x run.sh && ./run.sh"
local local_exec_cmd="export WORKSPACE_DIR=\$PWD && cd $container_dest && chmod +x run.sh && ./run.sh"
local remote_exec_cmd="export WORKSPACE_DIR=\\\$PWD && cd $container_dest && chmod +x run.sh && ./run.sh"
local ret_code=0
if [[ "$is_local" == "true" ]]; then
docker exec "$container" bash -c "$exec_cmd"
docker exec "$container" bash -c "$local_exec_cmd"
ret_code=$?
else
$cmd_prefix docker exec "$container" bash -c "\"$exec_cmd\""
$cmd_prefix docker exec "$container" bash -c "\"$remote_exec_cmd\""
ret_code=$?
fi