mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-21 05:07:04 +00:00
82ab6cc96e
- TC-INFERENCE-003: Add unload step for gemma3:4b at end - TC-INFERENCE-004: Remove redundant 4b unload at start - TC-INFERENCE-005: Remove redundant 12b unload at start Each model size test now handles its own VRAM cleanup. Workflow-level unload remains as safety fallback for failures. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
106 lines
3.3 KiB
YAML
106 lines
3.3 KiB
YAML
id: TC-INFERENCE-003
|
|
name: API Endpoint Test
|
|
suite: inference
|
|
priority: 3
|
|
timeout: 120000
|
|
|
|
dependencies:
|
|
- TC-INFERENCE-001
|
|
|
|
steps:
|
|
- name: Test generate endpoint (non-streaming)
|
|
command: |
|
|
curl -s http://localhost:11434/api/generate \
|
|
-d '{"model":"gemma3:4b","prompt":"Say hello in one word","stream":false}' \
|
|
| head -c 500
|
|
|
|
- name: Test generate endpoint (streaming)
|
|
command: |
|
|
curl -s http://localhost:11434/api/generate \
|
|
-d '{"model":"gemma3:4b","prompt":"Count from 1 to 3","stream":true}' \
|
|
| head -5
|
|
|
|
- name: Verify API requests logged successfully
|
|
command: |
|
|
cd docker
|
|
LOGS=$(docker compose logs --since=5m 2>&1)
|
|
|
|
echo "=== API Request Log Verification ==="
|
|
|
|
# Check for generate requests with 200 status
|
|
GENERATE_200=$(echo "$LOGS" | grep -c '\[GIN\].*200.*POST.*/api/generate' || echo "0")
|
|
echo "Generate requests with 200 status: $GENERATE_200"
|
|
|
|
if [ "$GENERATE_200" -gt 0 ]; then
|
|
echo "SUCCESS: API generate requests completed successfully"
|
|
echo "$LOGS" | grep '\[GIN\].*POST.*/api/generate' | tail -3
|
|
else
|
|
echo "WARNING: No successful generate requests found in recent logs"
|
|
fi
|
|
|
|
- name: Check for API errors in logs
|
|
command: |
|
|
cd docker
|
|
LOGS=$(docker compose logs --since=5m 2>&1)
|
|
|
|
echo "=== API Error Check ==="
|
|
|
|
# Check for 4xx/5xx errors on generate endpoint
|
|
if echo "$LOGS" | grep -qE '\[GIN\].*(4[0-9]{2}|5[0-9]{2}).*POST.*/api/generate'; then
|
|
echo "WARNING: API errors found on generate endpoint:"
|
|
echo "$LOGS" | grep -E '\[GIN\].*(4[0-9]{2}|5[0-9]{2}).*POST.*/api/generate' | tail -3
|
|
else
|
|
echo "SUCCESS: No API errors on generate endpoint"
|
|
fi
|
|
|
|
# Check for any CUDA errors during API processing
|
|
if echo "$LOGS" | grep -qE "(CUBLAS_STATUS_|CUDA error)"; then
|
|
echo "CRITICAL: CUDA errors during API processing:"
|
|
echo "$LOGS" | grep -E "(CUBLAS_STATUS_|CUDA error)"
|
|
exit 1
|
|
fi
|
|
|
|
echo "SUCCESS: No critical errors during API processing"
|
|
|
|
- name: Display API response times from logs
|
|
command: |
|
|
cd docker
|
|
LOGS=$(docker compose logs --since=5m 2>&1)
|
|
|
|
echo "=== API Response Times ==="
|
|
|
|
# Show recent generate request response times
|
|
echo "$LOGS" | grep -E '\[GIN\].*POST.*/api/generate' | tail -5 | while read line; do
|
|
# Extract response time from GIN log format
|
|
echo "$line" | grep -oE '[0-9]+(\.[0-9]+)?(ms|s|m)' | head -1
|
|
done
|
|
|
|
echo ""
|
|
echo "Recent API requests:"
|
|
echo "$LOGS" | grep '\[GIN\]' | tail -5
|
|
|
|
- name: Unload model after 4b tests complete
|
|
command: |
|
|
echo "Unloading gemma3:4b from VRAM..."
|
|
curl -s http://localhost:11434/api/generate -d '{"model":"gemma3:4b","keep_alive":0}' || true
|
|
sleep 2
|
|
echo "Model unloaded"
|
|
|
|
criteria: |
|
|
Ollama REST API should handle inference requests.
|
|
|
|
Expected for non-streaming:
|
|
- Returns JSON with "response" field
|
|
- Response contains some greeting (hello, hi, etc.)
|
|
|
|
Expected for streaming:
|
|
- Returns multiple JSON lines
|
|
- Each line contains partial response
|
|
|
|
Log verification:
|
|
- Generate API requests logged with 200 status
|
|
- NO 4xx/5xx errors on generate endpoint
|
|
- NO CUDA/CUBLAS errors during API processing
|
|
|
|
Accept any valid JSON response. Content may vary.
|