Add multi-GPU test workflow and rename single-GPU workflow

- Rename tesla-k80-tests.yml to tesla-k80-single-gpu-tests.yml for clarity
- Add new tesla-k80-multi-gpu-tests.yml workflow for large models
- Add multi-gpu profile to test/config/models.yaml with gemma3:27b and gpt-oss:20b
- Multi-GPU workflow includes GPU count verification and weekly schedule
- Profile-specific validation allows multi-GPU splits for large models
- Separate workflows optimize CI efficiency: quick tests vs. thorough tests
This commit is contained in:
Shang Chieh Tseng
2025-10-30 12:04:50 +08:00
parent 1aa80e9411
commit 6c3876a30d
3 changed files with 110 additions and 10 deletions

View File

@@ -0,0 +1,87 @@
name: Tesla K80 Single-GPU Tests
on:
workflow_dispatch: # Manual trigger only
jobs:
test:
runs-on: self-hosted
timeout-minutes: 60
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Verify ollama binary exists
run: |
if [ ! -f ./ollama ]; then
echo "Error: ollama binary not found. Please run the build workflow first."
exit 1
fi
ls -lh ollama
- name: Build test-runner
run: |
cd cmd/test-runner
go mod init github.com/ollama/ollama/cmd/test-runner || true
go mod tidy
go build -o ../../test-runner .
cd ../..
ls -lh test-runner
- name: Validate test configuration
run: |
./test-runner validate --config test/config/quick.yaml
- name: Run quick tests
run: |
./test-runner run --profile quick --config test/config/quick.yaml --output test-report-quick --verbose
timeout-minutes: 10
- name: Check quick test results
run: |
if ! jq -e '.summary.failed == 0' test-report-quick.json; then
echo "Quick tests failed!"
jq '.results[] | select(.status == "FAILED")' test-report-quick.json
exit 1
fi
echo "Quick tests passed!"
- name: Upload quick test results
if: always()
uses: actions/upload-artifact@v4
with:
name: quick-test-results
path: |
test-report-quick.json
test-report-quick.md
ollama.log
retention-days: 7
- name: Run full tests (if quick tests passed)
if: success()
run: |
./test-runner run --profile full --config test/config/models.yaml --output test-report-full --verbose
timeout-minutes: 45
- name: Check full test results
if: success()
run: |
if ! jq -e '.summary.failed == 0' test-report-full.json; then
echo "Full tests failed!"
jq '.results[] | select(.status == "FAILED")' test-report-full.json
exit 1
fi
echo "All tests passed!"
- name: Upload full test results
if: always()
uses: actions/upload-artifact@v4
with:
name: full-test-results
path: |
test-report-full.json
test-report-full.md
ollama.log
retention-days: 14