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 9, 07:30 UTC
[Misc] Clean up HIDDEN_DEPRECATED_METRICS after metric removal (#33323)
Signed-off-by: carlory <baofa.fan@daocloud.io> Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
杨朱 · Kiki committed
Jan 30, 2026 at 21:31 UTC
cf896ae0e3cde7670076fc7323a1afb71228697d
1 file changed
+1
-5
tests/entrypoints/instrumentator/test_metrics.py
+1
-5
@@ -231,11 +231,7 @@ EXPECTED_METRICS_MM = [
231
"vllm:mm_cache_hits",
232
]
233
234
-HIDDEN_DEPRECATED_METRICS: list[str] = [
235
- "vllm:gpu_cache_usage_perc",
236
- "vllm:gpu_prefix_cache_queries",
237
- "vllm:gpu_prefix_cache_hits",
238
-]
234
+HIDDEN_DEPRECATED_METRICS: list[str] = []
235
236
237
@pytest.mark.asyncio