Skip to main content

cmind/modelmanager/v1/model_deployment_observability_service.proto

Package: cmind.modelmanager.v1

Enums

MetricsStep

ValueNumberDescription
METRICS_STEP_UNSPECIFIED0
METRICS_STEP_1M1
METRICS_STEP_5M2
METRICS_STEP_15M3
METRICS_STEP_30M4
METRICS_STEP_1H5
METRICS_STEP_2H6
METRICS_STEP_6H7
METRICS_STEP_12H8
METRICS_STEP_1D9

Messages

GetModelDeploymentGpuOverviewRequest

GetModelDeploymentGpuOverviewResponse

FieldTypeNumberDescription
nodesrepeated GpuNode1
deploymentsrepeated ModelDeploymentGpuSummary2

GpuNode

FieldTypeNumberDescription
nodeNamestring1
gpusrepeated GpuDevice2

GpuDevice

FieldTypeNumberDescription
idstring1
uuidstring2
modelstring3
totalVramMibint644
usedVramMiboptional int645
freeVramMiboptional int646

ModelDeploymentGpuSummary

FieldTypeNumberDescription
uidstring1
namestring2
gpusrepeated GpuUsage3

GpuUsage

FieldTypeNumberDescription
nodeNamestring1
gpuIdstring2
gpuUuidstring3
usedVramMibint644

GetModelDeploymentMetricsRequest

FieldTypeNumberDescription
deploymentNamestring1
startTimeuint322
endTimeuint323
stepMetricsStep4

GetModelDeploymentMetricsResponse

FieldTypeNumberDescription
timeRangeMetricsTimeRange1
metricsModelDeploymentMetrics2

MetricsTimeRange

FieldTypeNumberDescription
startuint321
enduint322
stepMetricsStep3

MetricPoint

FieldTypeNumberDescription
timestampuint321
valuedouble2

ModelDeploymentMetrics

FieldTypeNumberDescription
totalRequestsrepeated MetricPoint1
total4xxErrorsrepeated MetricPoint2
total5xxErrorsrepeated MetricPoint3
p50Latencyrepeated MetricPoint4
p90Latencyrepeated MetricPoint5
p99Latencyrepeated MetricPoint6
totalPromptTokensrepeated MetricPoint7
totalCompletionTokensrepeated MetricPoint8
totalEmbeddingTokensrepeated MetricPoint9
totalTokensrepeated MetricPoint10
totalRerankTokensrepeated MetricPoint11

ListNodeModelCacheUsageRequest

ListNodeModelCacheUsageResponse

FieldTypeNumberDescription
nodesrepeated NodeModelCacheUsage1Per GPU node holding the model-weight cache.

NodeModelCacheUsage

NodeModelCacheUsage describes the filesystem backing the model-weight cache on a single node, plus the models cached there.

FieldTypeNumberDescription
nodeNamestring1
cachePathstring2Cache root on the node (the configured base path, e.g. /mnt/llm_cache).
capacityBytesoptional int643Filesystem totals for the mount backing the cache root. Optional rather than erroring the whole list: they come from a best-effort metrics source (node-exporter via Prometheus) and are absent when that's unavailable for a node/mount, while the cache listing from Kubernetes stays valid.
usedBytesoptional int644
availableBytesoptional int645
modelsrepeated CachedModelUsage6Models cached on this node.

CachedModelUsage

CachedModelUsage is one model cached on a node and its footprint there. (CachedModel is already taken in this package for the deployment-side model reference, so this carries the Usage suffix.)

FieldTypeNumberDescription
modelUrlstring1
displayNamestring2
sizeBytesoptional int643Weight-file size of the model (best-effort, from HuggingFace repo metadata, which tracks the on-disk size closely). Absent when the size can't be determined — a non-HuggingFace source, or a lookup that failed.
deploymentNamesrepeated string4Deployments referencing this cached model (sorted), so the UI can show when several deployments share one cache.

Services

ModelDeploymentObservabilityService

GetModelDeploymentGpuOverview

GET /cmind.modelmanager.v1.ModelDeploymentObservabilityService/GetModelDeploymentGpuOverview

Request: GetModelDeploymentGpuOverviewRequest

Response: GetModelDeploymentGpuOverviewResponse

GetModelDeploymentMetrics

GET /cmind.modelmanager.v1.ModelDeploymentObservabilityService/GetModelDeploymentMetrics

Request: GetModelDeploymentMetricsRequest

Response: GetModelDeploymentMetricsResponse

ListNodeModelCacheUsage

GET /cmind.modelmanager.v1.ModelDeploymentObservabilityService/ListNodeModelCacheUsage

ListNodeModelCacheUsage reports the node-local model-weight cache: per-node filesystem capacity/usage and, per node, the cached models and their sizes.

Request: ListNodeModelCacheUsageRequest

Response: ListNodeModelCacheUsageResponse