[HiSparse] Log steady-state max concurrency and expose host-tier utilization gauges (#58949)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Robert Shaw
2026-10-05 14:20:32 -07:00
committed by GitHub
co-authored by Claude Opus 5.5 Matthew Bonanni
parent 8542c3eff5
commit 2e3154aa18
12 changed files with 323 additions and 34 deletions
+8
View File
@@ -37,6 +37,14 @@ memory consumption is therefore topology- and implementation-dependent. The
realized capacity may be slightly smaller because the budget is rounded down
to complete host blocks.
Startup logs report two concurrency bounds at `max_model_len`. The generic
`Maximum concurrency` line charges each request its full admission footprint,
including the in-flight window of every resident group. The `HiSparse
steady-state maximum concurrency` line charges running requests that read from
host only their active tail pages, plus one request being admitted at its full
footprint. Host-pool metrics are listed in
[Metrics](../usage/metrics.md#hisparse-kv-connector-metrics).
## Ownership
| Thing | Owner | What “owner” means |
@@ -23,6 +23,10 @@ METRIC_SOURCE_FILES = [
"path": "vllm/distributed/kv_transfer/kv_connector/v1/nixl/stats.py",
"key": "metrics-nixl",
},
{
"path": "vllm/distributed/kv_transfer/kv_connector/v1/hisparse/stats.py",
"key": "metrics-hisparse",
},
{
"path": "vllm/v1/simple_kv_offload/metrics.py",
"key": "metrics-simple-kv-offload",
+9
View File
@@ -45,6 +45,15 @@ The following metrics are exposed:
--8<-- "gen:metrics-nixl"
## HiSparse KV Connector Metrics
These metrics are exposed when the `HiSparseConnector` KV connector is
configured. The host-pool gauges are reported by the scheduler once per engine
step, for the host pool shared by all tensor-parallel ranks; evictable cached
blocks count as free.
--8<-- "gen:metrics-hisparse"
## Simple CPU Offload Connector Metrics
These metrics are exposed when the `SimpleCPUOffloadConnector` KV connector