NVIDIA Run:ai

Pods

Retrieve data about workload pods from your NVIDIA Run:ai platform.

List pods.

Retrieve a list of pods from a cluster.

SecuritybearerAuth
Request
query Parameters
deleted
boolean

Return only deleted resources when true.

offset
integer <int32>

The offset of the first item returned in the collection.

Example: offset=100
limit
integer <int32> [ 1 .. 500 ]
Default: 50

The maximum number of entries to return.

sortOrder
string
Default: "asc"

Sort results in descending or ascending order.

Enum: "asc" "desc"
sortBy
string

Sort results using a parameter.

Enum: "clusterId" "workloadId" "revisionId" "nodeName" "currentNodepool" "createdAt" "completedAt" "deletedAt"
filterBy
Array of strings

Filter results using a parameter. Use the format field-name operator value. Operators are == Equals, != Not equals, <= Less than or equal, >= Greater than or equal, =@ contains, !@ Does not contains, =^ Starts with and =$ Ends with. Dates are in ISO 8601 timestamp format and available for operators ==, !=, <= and >=.

Example: filterBy=nodeName!=some-node-name
verbosity
string (PodVerbosity)
Default: "brief"

response verbosity level. if full, the response includes workloadName and projectName fields.

Enum: "brief" "full"
Example: verbosity=full
completed
string
Default: "all"

Return only completed resources when 'true', return only non-completed resources when 'false'. By default, or when empty, returns all resources.

search
string

Filter results by a free text search.

Example: search=test project
Responses
200

Executed successfully.

401

Unauthorized

403

Forbidden

404

The specified resource was not found

500

unexpected error

503

unexpected error

get/api/v1/workloads/pods
Response samples
application/json
{
  • "next": 1,
  • "pods": [
    ]
}

Get pod metrics data.

Retrieve pod's metrics data for use in analysis applications.

SecuritybearerAuth
Request
path Parameters
workloadId
required
string <uuid>

The Universally Unique Identifier (UUID) of the workload.

podId
required
string <uuid>

The requested pod id.

query Parameters
metricType
required
Array of strings (PodMetricType)

Specify which metric data to request. Advanced GPU metrics are only supported if the 'Advanced GPU Metrics' feature flag in the settings is enabled.

Items Enum: "GPU_UTILIZATION_PER_GPU" "GPU_UTILIZATION" "GPU_MEMORY_USAGE_BYTES_PER_GPU" "GPU_MEMORY_USAGE_BYTES" "CPU_USAGE_CORES" "CPU_MEMORY_USAGE_BYTES" "GPU_GRAPHICS_ENGINE_ACTIVITY_PER_GPU" "GPU_SM_ACTIVITY_PER_GPU" "GPU_SM_OCCUPANCY_PER_GPU" "GPU_TENSOR_ACTIVITY_PER_GPU" "GPU_FP64_ENGINE_ACTIVITY_PER_GPU" "GPU_FP32_ENGINE_ACTIVITY_PER_GPU" "GPU_FP16_ENGINE_ACTIVITY_PER_GPU" "GPU_MEMORY_BANDWIDTH_UTILIZATION_PER_GPU" "GPU_NVLINK_TRANSMITTED_BANDWIDTH_PER_GPU" "GPU_NVLINK_RECEIVED_BANDWIDTH_PER_GPU" "GPU_PCIE_TRANSMITTED_BANDWIDTH_PER_GPU" "GPU_PCIE_RECEIVED_BANDWIDTH_PER_GPU" "GPU_SWAP_MEMORY_BYTES_PER_GPU" "NIM_NUM_REQUESTS_RUNNING" "NIM_NUM_REQUESTS_WAITING" "NIM_NUM_REQUEST_MAX" "NIM_REQUEST_SUCCESS_TOTAL" "NIM_REQUEST_FAILURE_TOTAL" "NIM_GPU_CACHE_USAGE_PERC" "NIM_TIME_TO_FIRST_TOKEN_SECONDS" "NIM_E2E_REQUEST_LATENCY_SECONDS" "NIM_TIME_TO_FIRST_TOKEN_SECONDS_PERCENTILES" "NIM_E2E_REQUEST_LATENCY_SECONDS_PERCENTILES" "DCGM_FI_DEV_NVLINK_BANDWIDTH_TOTAL" "DCGM_FI_DEV_NVLINK_BANDWIDTH_TOTAL_PER_GPU"
start
required
string <date-time>

Start date of time range to fetch data in ISO 8601 timestamp format.

Example: start=2023-06-06T12:09:18.211Z
end
required
string <date-time>

End date of time range to fetch data in ISO 8601 timestamp format.

Example: end=2023-06-07T12:09:18.211Z
numberOfSamples
integer [ 0 .. 1000 ]
Default: 20

The number of samples to take in the specified time range.

Example: numberOfSamples=20
Responses
200

Executed successfully.

207

Partial success.

400

Bad request.

401

Unauthorized

403

Forbidden

404

The specified resource was not found

500

unexpected error

503

unexpected error

get/api/v1/workloads/{workloadId}/pods/{podId}/metrics
Response samples
{
  • "measurements": [
    ],
  • "histogram": [
    ]
}

Get workload pods by id.

Retrieve the details of workload pods by workload id.

SecuritybearerAuth
Request
path Parameters
workloadId
required
string <uuid>

The Universally Unique Identifier (UUID) of the workload.

query Parameters
deleted
boolean

Return only deleted resources when true.

offset
integer <int32>

The offset of the first item returned in the collection.

Example: offset=100
limit
integer <int32> [ 1 .. 500 ]
Default: 50

The maximum number of entries to return.

search
string

Filter results by a free text search.

Example: search=test project
Responses
200

Executed successfully.

401

Unauthorized

403

Forbidden

404

The specified resource was not found

500

unexpected error

503

unexpected error

get/api/v1/workloads/{workloadId}/pods
Response samples
application/json
{
  • "next": 1,
  • "pods": [
    ]
}

Get pods count.

Retrieve the number of pods from a cluster.

SecuritybearerAuth
Request
query Parameters
deleted
boolean

Return only deleted resources when true.

filterBy
Array of strings

Filter results using a parameter. Use the format field-name operator value. Operators are == Equals, != Not equals, <= Less than or equal, >= Greater than or equal, =@ contains, !@ Does not contains, =^ Starts with and =$ Ends with. Dates are in ISO 8601 timestamp format and available for operators ==, !=, <= and >=.

Example: filterBy=nodeName!=some-node-name
search
string

Filter results by a free text search.

Example: search=test project
Responses
200

Executed successfully.

401

Unauthorized

403

Forbidden

500

unexpected error

503

unexpected error

get/api/v1/workloads/pods/count
Response samples
application/json
{
  • "count": 1
}

Get revision pods by id. [Experimental]

Retrieve the details of revision pods by revision id. Supported for clusters v2.21+.

SecuritybearerAuth
Request
path Parameters
revisionId
required
string <uuid>

The Universally Unique Identifier (UUID) of the revision.

query Parameters
deleted
boolean

Return only deleted resources when true.

Responses
200

Executed successfully.

401

Unauthorized

403

Forbidden

404

The specified resource was not found

500

unexpected error

503

unexpected error

get/api/v1/workloads/inferences/revisions/{revisionId}/pods
Response samples
application/json
{
  • "pods": [
    ]
}
➔ Next to Workloads