Files

102 lines
4.2 KiB
YAML

name: Upload CUDA Coredumps
description: Upload CUDA coredump files as artifacts, optionally signal to a tracker issue, and clean up.
inputs:
artifact-suffix:
description: Suffix appended to the artifact name (e.g. matrix partition id)
required: false
default: ""
retention-days:
description: Number of days to retain the artifact
required: false
default: "7"
tracker-issue:
description: |
If set, post a one-line comment to sgl-project/sglang issue
#<tracker-issue> when at least one coredump is detected. Requires
`bot-token` with issues:write on sgl-project/sglang.
required: false
default: ""
bot-token:
description: PAT with issues:write on sgl-project/sglang. Required when tracker-issue is set.
required: false
default: ""
runs:
using: composite
steps:
- name: Check for coredumps
id: check
shell: bash
run: |
# Mirror get_dump_dir() in python/sglang/srt/debug_utils/cuda_coredump.py:
# explicit override > per-job RUNNER_TEMP > /tmp default, then a
# per-(run, attempt) subdir so dumps are never mis-attributed across CI
# jobs that share a self-hosted runner's filesystem.
if [ -n "$SGLANG_CUDA_COREDUMP_DIR" ]; then
base="$SGLANG_CUDA_COREDUMP_DIR"
elif [ -n "$RUNNER_TEMP" ]; then
base="$RUNNER_TEMP/sglang_cuda_coredumps"
else
base="/tmp/sglang_cuda_coredumps"
fi
if [ -n "$GITHUB_RUN_ID" ]; then
dir="$base/${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT:-1}"
else
dir="$base"
fi
echo "dump_dir=$dir" >> "$GITHUB_OUTPUT"
if [ -d "$dir" ] && [ -n "$(ls -A "$dir" 2>/dev/null)" ]; then
echo "has_dumps=true" >> "$GITHUB_OUTPUT"
else
echo "has_dumps=false" >> "$GITHUB_OUTPUT"
fi
- name: Upload CUDA coredumps
if: steps.check.outputs.has_dumps == 'true'
uses: actions/upload-artifact@v4
with:
name: cuda-coredumps-${{ github.job }}${{ inputs.artifact-suffix && format('-{0}', inputs.artifact-suffix) }}
path: ${{ steps.check.outputs.dump_dir }}/
retention-days: ${{ inputs.retention-days }}
- name: Signal coredump to tracker issue
if: steps.check.outputs.has_dumps == 'true' && inputs.tracker-issue != '' && inputs.bot-token != ''
shell: bash
env:
BOT_TOKEN: ${{ inputs.bot-token }}
PR_NUM: ${{ github.event.pull_request.number }}
EVENT_NAME: ${{ github.event_name }}
TRACKER_ISSUE: ${{ inputs.tracker-issue }}
run: |
if [ -n "$PR_NUM" ]; then
ref_label="PR #${PR_NUM}"
else
ref_label="$EVENT_NAME"
fi
# Resolve own job_id via REST API: match by runner_name + status
# in_progress (the current job is the only one in_progress on this
# runner). Robust across matrix expansions and artifact-suffix shapes.
job_id=$(curl -sS \
-H "Authorization: Bearer ${BOT_TOKEN}" \
-H "Accept: application/vnd.github+json" \
"${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/attempts/${GITHUB_RUN_ATTEMPT}/jobs?per_page=100" \
| python3 -c 'import json,sys,os; print(next((j["id"] for j in json.load(sys.stdin)["jobs"] if j.get("runner_name")==os.environ["RUNNER_NAME"] and j.get("status")=="in_progress"), ""))')
if [ -n "$job_id" ]; then
run_url="${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/job/${job_id}"
else
# Fallback to run-attempt URL if job_id lookup failed
run_url="${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/attempts/${GITHUB_RUN_ATTEMPT}"
fi
body_json=$(printf '{"body":"@hnyls2002 [Coredump Tracker] %s - %s"}' "${ref_label}" "${run_url}")
curl -sS -X POST \
-H "Authorization: Bearer ${BOT_TOKEN}" \
-H "Accept: application/vnd.github+json" \
-H "X-GitHub-Api-Version: 2022-11-28" \
"https://api.github.com/repos/sgl-project/sglang/issues/${TRACKER_ISSUE}/comments" \
-d "${body_json}"
- name: Cleanup CUDA coredumps
shell: bash
run: rm -rf "${{ steps.check.outputs.dump_dir }}"