iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[kv_offload] fix(metrics): rename kv_offload_tiering_block_{queries,hits} → chunk (#52812)

Browse Source 
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
This commit is contained in:
Ronen Schaffer
2026-08-20 00:24:07 +00:00
committed by GitHub
parent 5bf0dbd6fd
commit 0a111cca2c
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
vllm/v1/kv_offload/tiering/base.py
+2 -2
View File
@@ -45,8 +45,8 @@ class TieringOffloadingMetrics:
WRITE_TIME = "vllm:kv_offload_tiering_write_time"
PROMOTION_JOB_FAILURES = "vllm:kv_offload_tiering_promotion_job_failures"
CASCADE_JOB_FAILURES = "vllm:kv_offload_tiering_cascade_job_failures"
BLOCK_QUERIES = "vllm:kv_offload_tiering_block_queries"
BLOCK_HITS = "vllm:kv_offload_tiering_block_hits"
BLOCK_QUERIES = "vllm:kv_offload_tiering_chunk_queries"
BLOCK_HITS = "vllm:kv_offload_tiering_chunk_hits"
PRIMARY_WRITE_USAGE_PERC = "vllm:kv_offload_tiering_primary_write_usage_perc"
PRIMARY_READ_USAGE_PERC = "vllm:kv_offload_tiering_primary_read_usage_perc"
PROMOTION_ALLOCATION_FAILURES = (