Profiler

The Dynamo Profiler is an automated performance analysis tool that measures model inference characteristics to optimize deployment configurations. It determines optimal tensor parallelism (TP) settings for prefill and decode phases, generates performance interpolation data, and enables SLA-driven autoscaling through the Planner.

Feature Matrix

Quick Start

Prerequisites

• Dynamo platform installed (see Installation Guide)
• Kubernetes cluster with GPU nodes (for DGDR-based profiling)
• kube-prometheus-stack installed (required for SLA planner)

Using DynamoGraphDeploymentRequest (Recommended)

The recommended way to profile models is through DGDRs, which automate the entire profiling and deployment workflow.

1
apiVersion: nvidia.com/v1beta1
2
kind: DynamoGraphDeploymentRequest
3
metadata:
4
  name: my-model-profiling
5
spec:
6
  model: "Qwen/Qwen3-0.6B"
7
  backend: vllm
8
  image: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.0"
9
10
  workload:
11
    isl: 3000      # Average input sequence length
12
    osl: 150       # Average output sequence length
13
14
  sla:
15
    ttft: 200.0    # Target Time To First Token (ms)
16
    itl: 20.0      # Target Inter-Token Latency (ms)
17
18
  autoApply: true

$
kubectl apply -f my-profiling-dgdr.yaml -n $NAMESPACE

Using AI Configurator (Fast Offline Profiling)

AI Configurator enables rapid offline profiling (~30 seconds) and supports all backends (vLLM, SGLang, TensorRT-LLM). Since searchStrategy: rapid is the default, AIC is used automatically unless you explicitly set searchStrategy: thorough.

Configuration

Profiling Methods

Output

The profiler generates:

1. Optimal Configuration: Recommended TP sizes for prefill and decode engines
2. Performance Data: Interpolation models for the SLA Planner
3. Generated DGD: Complete deployment manifest with optimized settings

Example recommendations:

Suggested prefill TP:4 (TTFT 48.37 ms, throughput 15505.23 tokens/s/GPU)
Suggested decode TP:4 (ITL 4.83 ms, throughput 51.22 tokens/s/GPU)

Next Steps