monitor metrics of tokens per step using cudagraph batchsizes (#11031)

Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-09 22:35:36 -08:00
parent 28b3a1c7e5
commit ebf778061d
4 changed files with 23 additions and 13 deletions
--- a/tests/metrics/test_metrics.py
+++ b/tests/metrics/test_metrics.py
@@ -411,7 +411,7 @@ def test_engine_log_metrics_ray(
        logger = _RayPrometheusStatLogger(
            local_interval=0.5,
            labels=dict(model_name=engine.model_config.served_model_name),
-            max_model_len=engine.model_config.max_model_len)
+            vllm_config=engine.vllm_config)
        engine.add_logger("ray", logger)
        for i, prompt in enumerate(example_prompts):
            engine.add_request(