Skip to content

Update server address write logic #229

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
XkunW merged 2 commits into from
Apr 8, 2026
Merged

Update server address write logic #229

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3a06105
Add retry loop for writing server address to job json file, rename te…
XkunW Apr 8, 2026
f8a7f2c
Merge branch 'main' into bugfix/misc
XkunW Apr 8, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 18 additions & 8 deletions vec_inf/client/_slurm_templates.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -186,10 +186,15 @@ class SlurmScriptTemplate(TypedDict):
],
"write_to_json": [
'\njson_path="{log_dir}/{model_name}.$SLURM_JOB_ID/{model_name}.$SLURM_JOB_ID.json"',
'jq --arg server_addr "$server_address" \\',
" '. + {{\"server_address\": $server_addr}}' \\",
' "$json_path" > temp.json \\',
' && mv temp.json "$json_path"',
'tmp_json="${{json_path}}.tmp.$$"',
"for _attempt in 1 2 3 4 5; do",
' jq --arg server_addr "$server_address" \\',
" '. + {{\"server_address\": $server_addr}}' \\",
' "$json_path" > "$tmp_json" \\',
' && mv "$tmp_json" "$json_path" \\',
" && break",
" sleep 2",
"done",
],
"launch_cmd": {
"vllm": [
Expand Down Expand Up @@ -303,10 +308,15 @@ class BatchModelLaunchScriptTemplate(TypedDict):
"write_to_json": [
"het_job_id=$(($SLURM_JOB_ID+{het_group_id}))",
'json_path="{log_dir}/{slurm_job_name}.$het_job_id/{model_name}.$het_job_id.json"',
'jq --arg server_addr "$server_address" \\',
" '. + {{\"server_address\": $server_addr}}' \\",
' "$json_path" > temp_{model_name}.json \\',
' && mv temp_{model_name}.json "$json_path"\n',
'tmp_json="${{json_path}}.tmp.$$"',
"for _attempt in 1 2 3 4 5; do",
' jq --arg server_addr "$server_address" \\',
" '. + {{\"server_address\": $server_addr}}' \\",
' "$json_path" > "$tmp_json" \\',
' && mv "$tmp_json" "$json_path" \\',
" && break",
" sleep 2",
"done\n",
],
"container_command": f"{CONTAINER_MODULE_NAME} exec --nv --containall {{image_path}} \\",
"launch_cmd": {
Expand Down