diff options
| author | Pierrick Hymbert <pierrick.hymbert@gmail.com> | 2024-04-06 05:40:47 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-04-06 05:40:47 +0200 |
| commit | 75cd4c77292034ecec587ecb401366f57338f7c0 (patch) | |
| tree | de137718780505410bc75ce219f4bc164961c4fd /examples/server/bench/bench.py | |
| parent | a8bd14d55717754a1f48313a846a2b16fa998ad2 (diff) | |
ci: bench: support sse and fix prompt processing time / server: add tokens usage in stream OAI response (#6495)
* ci: bench: support sse and fix prompt processing time
server: add tokens usage in stream mode
* ci: bench: README.md EOL
* ci: bench: remove total pp and tg as it is not accurate
* ci: bench: fix case when there is no token generated
* ci: bench: change to the 95 percentile for pp and tg as it is closer to what the server exports in metrics
* ci: bench: fix finish reason rate
Diffstat (limited to 'examples/server/bench/bench.py')
| -rw-r--r-- | examples/server/bench/bench.py | 11 |
1 files changed, 5 insertions, 6 deletions
diff --git a/examples/server/bench/bench.py b/examples/server/bench/bench.py index 86eeeccf..6ca637bd 100644 --- a/examples/server/bench/bench.py +++ b/examples/server/bench/bench.py @@ -76,7 +76,6 @@ def main(args_in: list[str] | None = None) -> None: data['metrics'][metric_name][metric_metric]=value github_env.write( f"{escape_metric_name(metric_name)}_{escape_metric_name(metric_metric)}={value}\n") - token_seconds = data['metrics']['llamacpp_tokens_second']['avg'] iterations = data['root_group']['checks']['success completion']['passes'] except Exception: @@ -181,16 +180,16 @@ xychart-beta bench_results = { "i": iterations, "req": { - "p90": round(data['metrics']["http_req_duration"]["p(90)"], 2), + "p95": round(data['metrics']["http_req_duration"]["p(95)"], 2), "avg": round(data['metrics']["http_req_duration"]["avg"], 2), }, "pp": { - "p90": round(data['metrics']["llamacpp_prompt_tokens"]["p(90)"], 2), - "avg": round(data['metrics']["llamacpp_prompt_tokens"]["avg"], 2), + "p95": round(data['metrics']["llamacpp_prompt_processing_second"]["p(95)"], 2), + "avg": round(data['metrics']["llamacpp_prompt_processing_second"]["avg"], 2), "0": round(mean(prometheus_metrics['prompt_tokens_seconds']), 2), }, "tg": { - "p90": round(data['metrics']["llamacpp_tokens_second"]["p(90)"], 2), + "p95": round(data['metrics']["llamacpp_tokens_second"]["p(95)"], 2), "avg": round(data['metrics']["llamacpp_tokens_second"]["avg"], 2), "0": round(mean(prometheus_metrics['predicted_tokens_seconds']), 2), }, @@ -206,7 +205,7 @@ xychart-beta def start_benchmark(args): - k6_path = 'k6' + k6_path = './k6' if 'BENCH_K6_BIN_PATH' in os.environ: k6_path = os.environ['BENCH_K6_BIN_PATH'] k6_args = [ |