slug: triton
provider: Triton Inference Server
generated_by: planning/capability-mapping/scripts/classify_capabilities.py
model: claude-opus-5
frame:
- Banking & Capital Markets
- Software & Technology
min_confidence: 0.7
capability_model:
  source: https://github.com/vincentmakes/turbo-ea-capabilities
  license: CC-BY-4.0
  attribution: Turbo EA Capabilities by Vincent Verdet — Turbo EA, https://github.com/vincentmakes/turbo-ea-capabilities,
    CC BY 4.0
  notice: NOTICE
edge_count: 2
edges:
- tag: Inference
  spec_file: triton-inference-api-openapi.yml
  capability_id: BC-610.60
  capability_id_l1: BC-610
  capability_name: Artificial Intelligence Management
  confidence: 0.8
  evidence: '''POST /v2/models/{model_name}/infer  modelInfer  Run Inference on a Model'''
  reason: Serving ML model predictions at runtime is the operational core of AI/ML model lifecycle and
    MLOps.
- tag: Model Repository
  spec_file: triton-model-repository-api-openapi.yml
  capability_id: BC-610.60
  capability_id_l1: BC-610
  capability_name: Artificial Intelligence Management
  confidence: 0.75
  evidence: '''Load or Reload a Model'' / ''List Models in the Repository'''
  reason: Model repository indexing and load/unload of models is ML model deployment lifecycle (MLOps)
    management.