litellm/scripts
Alexsander Hamir 69a65b4430 feat(benchmark): add RPS suite (10 runs 1k–10k RPS, one at a time, separate files)
- scripts/run_benchmark_rps_suite.py: run benchmark at 1k, 2k, ..., 10k RPS sequentially
- Each run writes to benchmark_results_<rps>rps.txt (e.g. benchmark_results_1000rps.txt)
- First run waits for proxy; runs 2–10 use --no-wait. --output-dir, --requests supported
- proxy_cli: LITELLM_AUTO_BENCHMARK_RPS_SUITE=1 runs suite when proxy is up
- Optional: LITELLM_AUTO_BENCHMARK_OUTPUT_DIR, LITELLM_AUTO_BENCHMARK_REQUESTS
2026-02-02 13:56:16 -08:00
..
health_check Add custom auth header support and increase default prompt size to 100k chars (#19436) 2026-01-20 13:25:12 -08:00
benchmark_proxy_vs_provider.py feat(benchmark): add RPS mode with --rps-control 2026-02-02 12:51:21 -08:00
create_litellm_branch.ps1 feat: add script to create branches with litellm_ prefix (#17606) 2025-12-06 10:41:39 -08:00
create_litellm_branch.sh enhance: create_litellm_branch tool to be more robust (#17874) 2025-12-12 05:35:50 -08:00
mock_grayswan_timeout_server.py implement failopen option default to True on grayswan guardrail (#18266) 2026-01-06 15:17:05 +05:30
run_benchmark_after_proxy.py feat(scripts): add run_benchmark_after_proxy to wait for proxy and save output to .txt 2026-02-02 13:26:11 -08:00
run_benchmark_rps_suite.py feat(benchmark): add RPS suite (10 runs 1k–10k RPS, one at a time, separate files) 2026-02-02 13:56:16 -08:00