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, 21:00 UTC
[V0][Metrics] Deprecate some KV/prefix cache metrics (#14136)
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Mark McLoughlin committed
Mar 3, 2025 at 18:25 UTC
2dfdfed8a0fe5517f8d4050740c251b1c1d35eeb
1 file changed
+25
-5
vllm/engine/metrics.py
+25
-5
@@ -74,31 +74,51 @@ class Metrics:
74
],
75
multiprocess_mode="livemostrecent",
76
)
77
+
78
+ # Deprecated in 0.8 - KV cache offloading is not used in V1
79
+ # TODO: in 0.9, only enable if show_hidden_metrics=True
80
self.gauge_scheduler_swapped = self._gauge_cls(
81
name="vllm:num_requests_swapped",
79
- documentation="Number of requests swapped to CPU.",
82
+ documentation=(
83
+ "Number of requests swapped to CPU. "
84
+ "DEPRECATED: KV cache offloading is not used in V1"),
85
labelnames=labelnames,
86
multiprocess_mode="sum")
87
+
88
# KV Cache Usage in %
89
self.gauge_gpu_cache_usage = self._gauge_cls(
90
name="vllm:gpu_cache_usage_perc",
91
documentation="GPU KV-cache usage. 1 means 100 percent usage.",
92
labelnames=labelnames,
93
multiprocess_mode="sum")
94
+
95
+ # Deprecated in 0.8 - KV cache offloading is not used in V1
96
+ # TODO: in 0.9, only enable if show_hidden_metrics=True
97
self.gauge_cpu_cache_usage = self._gauge_cls(
98
name="vllm:cpu_cache_usage_perc",
90
- documentation="CPU KV-cache usage. 1 means 100 percent usage.",
99
+ documentation=(
100
+ "CPU KV-cache usage. 1 means 100 percent usage. "
101
+ "DEPRECATED: KV cache offloading is not used in V1"),
102
labelnames=labelnames,
103
multiprocess_mode="sum")
93
- # Prefix caching block hit rate
104
+
105
+ # Deprecated in 0.8 - KV cache offloading is not used in V1
106
+ # TODO: in 0.9, only enable if show_hidden_metrics=True
107
self.gauge_cpu_prefix_cache_hit_rate = self._gauge_cls(
108
name="vllm:cpu_prefix_cache_hit_rate",
96
- documentation="CPU prefix cache block hit rate.",
109
+ documentation=(
110
+ "CPU prefix cache block hit rate. "
111
+ "DEPRECATED: KV cache offloading is not used in V1"),
112
labelnames=labelnames,
113
multiprocess_mode="sum")
114
+
115
+ # Deprecated in 0.8 - replaced by queries+hits counters in V1
116
+ # TODO: in 0.9, only enable if show_hidden_metrics=True
117
self.gauge_gpu_prefix_cache_hit_rate = self._gauge_cls(
118
name="vllm:gpu_prefix_cache_hit_rate",
101
- documentation="GPU prefix cache block hit rate.",
119
+ documentation=("GPU prefix cache block hit rate. "
120
+ "DEPRECATED: use vllm:gpu_prefix_cache_queries and "
121
+ "vllm:gpu_prefix_cache_queries in V1"),
122
labelnames=labelnames,
123
multiprocess_mode="sum")
124