profile_sla_dgdr.yaml

# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# DynamoGraphDeploymentRequest for online profiling (actual deployment testing)
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeploymentRequest
metadata:
  name: sla-online
spec:
  model: Qwen/Qwen3-0.6B
  backend: vllm

  # ProfilingConfig maps directly to the profile_sla.py config format
  profilingConfig:
    profilerImage: "nvcr.io/nvidian/dynamo-dev/vllm-runtime:dep-554.0"
    config:
      # Sweep/profiling configuration
      sweep:
        # Online profiling mode (real deployment testing)
        use_ai_configurator: false

      # SLA targets for profiling
      sla:
        isl: 3000   # Input sequence length
        osl: 150    # Output sequence length
        ttft: 200.0 # Time To First Token target (milliseconds)
        itl: 20.0   # Inter-Token Latency target (milliseconds)

  # Deployment overrides for the auto-created DGD
  deploymentOverrides:
    workersImage: "nvcr.io/nvidian/dynamo-dev/vllm-runtime:dep-554.0"

  # Automatically create DynamoGraphDeployment after profiling
  autoApply: true