A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 22:15 UTC
[ci] Fix metrics test model path (#13635)
Kevin H. Luu committed
Feb 20, 2025 at 22:12 UTC
34ad27fe8300c5de350b421d66c8a9b201734ac9
1 file changed
+1
-1
tests/metrics/test_metrics.py
+1
-1
@@ -146,7 +146,7 @@ def test_metric_set_tag_model_name(vllm_runner, model: str, dtype: str,
146
metrics_tag_content = stat_logger.labels["model_name"]
147
148
if served_model_name is None or served_model_name == []:
149
- actual_model_name = f"{MODEL_WEIGHTS_S3_BUCKET}/{model.split('/')[-1]}"
149
+ actual_model_name = f"{MODEL_WEIGHTS_S3_BUCKET}/{model}"
150
assert metrics_tag_content == actual_model_name, (
151
f"Metrics tag model_name is wrong! expect: {actual_model_name!r}\n"
152
f"actual: {metrics_tag_content!r}")