Triton Inference Server Trace API

openapi: 3.1.0
info:
  title: Triton Inference Server NVIDIA Triton Inference Server HTTP/REST CUDA Shared Memory Trace API
  description: RESTful API for the NVIDIA Triton Inference Server, implementing the KServe V2 inference protocol with Triton-specific extensions. Provides endpoints for model inference, health checks, server and model metadata, model repository management, statistics, tracing, logging, and system shared memory management.
  version: '2.0'
  contact:
    name: NVIDIA Triton Team
    url: https://github.com/triton-inference-server/server
    email: triton@nvidia.com
  license:
    name: BSD 3-Clause
    url: https://github.com/triton-inference-server/server/blob/main/LICENSE
servers:
- url: http://localhost:8000
  description: Triton HTTP endpoint (default)
- url: http://{host}:{port}
  description: Custom Triton HTTP endpoint
  variables:
    host:
      default: localhost
      description: Triton server hostname or IP
    port:
      default: '8000'
      description: Triton HTTP port
tags:
- name: Trace
  description: Request tracing configuration
paths:
  /v2/trace/setting:
    get:
      operationId: getTraceSetting
      summary: Triton Inference Server Get Trace Settings
      description: Retrieve the current global trace settings. This is a Triton extension to the KServe protocol.
      tags:
      - Trace
      responses:
        '200':
          description: Trace settings returned successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TraceSettingResponse'
        '400':
          description: Error retrieving trace settings
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
    post:
      operationId: updateTraceSetting
      summary: Triton Inference Server Update Trace Settings
      description: Update the global trace settings for request tracing.
      tags:
      - Trace
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/TraceSettingRequest'
      responses:
        '200':
          description: Trace settings updated successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TraceSettingResponse'
        '400':
          description: Error updating trace settings
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
  /v2/models/{model_name}/trace/setting:
    get:
      operationId: getModelTraceSetting
      summary: Triton Inference Server Get Model-Specific Trace Settings
      description: Retrieve the trace settings for a specific model.
      tags:
      - Trace
      parameters:
      - $ref: '#/components/parameters/modelName'
      responses:
        '200':
          description: Model trace settings returned successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TraceSettingResponse'
        '400':
          description: Error retrieving model trace settings
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
    post:
      operationId: updateModelTraceSetting
      summary: Triton Inference Server Update Model-Specific Trace Settings
      description: Update the trace settings for a specific model.
      tags:
      - Trace
      parameters:
      - $ref: '#/components/parameters/modelName'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/TraceSettingRequest'
      responses:
        '200':
          description: Model trace settings updated successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TraceSettingResponse'
        '400':
          description: Error updating model trace settings
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
components:
  schemas:
    TraceSettingRequest:
      type: object
      properties:
        trace_level:
          type: array
          description: Trace levels to set
          items:
            type: string
            enum:
            - 'OFF'
            - TIMESTAMPS
            - TENSORS
        trace_rate:
          type: string
          description: Trace sampling rate
        trace_count:
          type: string
          description: Maximum number of traces to collect (-1 for unlimited)
        log_frequency:
          type: string
          description: Frequency of trace log output
        trace_file:
          type: string
          description: File path for trace output
    ErrorResponse:
      type: object
      properties:
        error:
          type: string
          description: Error message describing what went wrong
    TraceSettingResponse:
      type: object
      properties:
        trace_level:
          type: array
          description: Current trace levels
          items:
            type: string
            enum:
            - 'OFF'
            - TIMESTAMPS
            - TENSORS
        trace_rate:
          type: string
          description: Trace sampling rate
        trace_count:
          type: string
          description: Maximum number of traces to collect
        log_frequency:
          type: string
          description: Frequency of trace log output
        trace_file:
          type: string
          description: File path for trace output
  parameters:
    modelName:
      name: model_name
      in: path
      required: true
      description: Name of the model
      schema:
        type: string
externalDocs:
  description: Triton Inference Server Protocol Documentation
  url: https://github.com/triton-inference-server/server/blob/main/docs/protocol/README.md