Update LLM Benchmark Data #328
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Update LLM Benchmark Data | |
| on: | |
| schedule: | |
| # Runs at 08:00 UTC every day | |
| - cron: "0 8 * * *" | |
| workflow_dispatch: | |
| jobs: | |
| run-benchmarks: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Send Benchmark Requests | |
| run: | | |
| # Pre-warm any spun-down instances (only audio right now) | |
| curl -f -X POST "https://ai-benchmarks.fly.dev/bench?mode=audio&max_tokens=20&num_requests=1" | |
| # Run the benchmarks | |
| declare -A max_tokens=( | |
| ["tools"]=100 | |
| ) | |
| default_max_tokens=20 | |
| regions=("sea" "iad" "cdg") | |
| media=("text" "tools" "image" "audio") | |
| for region in "${regions[@]}"; do | |
| for medium in "${media[@]}"; do | |
| echo "Running benchmarks for $medium in $region" | |
| max_tokens=${max_tokens[$medium]:-$default_max_tokens} | |
| curl -f -X POST "https://ai-benchmarks.fly.dev/bench?mode=$medium&max_tokens=$max_tokens&spread=30&store" -H "fly-prefer-region: $region" | |
| done | |
| done |