[Metrics][KV Offload] Add vllm:kv_offload_config_info - generic info metrics for offloading the offloading connector (#56867)

Signed-off-by: Amir Friedman <Amir.Friedman1@ibm.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
This commit is contained in:
Amir Friedman
2026-10-14 12:34:37 +00:00
committed by GitHub
co-authored by Claude Opus 5 Or Ozeri
parent 3a5a6b11a3
commit 775fefa804
17 changed files with 926 additions and 42 deletions
+10
View File
@@ -24,6 +24,7 @@ from vllm.v1.kv_offload.cpu.common import (
from vllm.v1.kv_offload.cpu.manager import CPUOffloadingManager
from vllm.v1.kv_offload.cpu.policies.arc import ARCCachePolicy
from vllm.v1.kv_offload.cpu.policies.lru import LRUCachePolicy
from vllm.v1.kv_offload.cpu.spec import CPUOffloadingSpec
def make_req_context(
@@ -238,6 +239,15 @@ def test_filter_reused_manager_reports_stores_skipped_counter():
assert stats.reduce()[CPUOffloadingMetrics.STORES_SKIPPED] == 0
def test_cpu_manager_fills_the_config_info_keys_of_the_spec():
"""A name the declaration misses becomes a dropped label at runtime."""
manager = make_cpu_manager(num_chunks=4)
(info,) = manager.config_info()
assert tuple(info) == CPUOffloadingSpec.config_info_keys({})
assert info["cpu_num_chunks"] == 4
def test_cpu_manager_reports_cache_usage_gauge():
def check_usage_stats(manager: CPUOffloadingManager, value: float):
stats = manager.get_stats()