Interconnect-Aware Accelerator Profiler using Google ADK and AgentFlow
Build an interconnect-aware profiler using Google ADK and AgentFlow to model distributed inference workloads across AWS Trainium and NVIDIA H100 clusters. The system must predict total latency within a 5% error margin while dynamically selecting optimal tensor-parallel configurations.
What you are building
The core problem, expected build, and operating context for this challenge.
Utilize Google ADK and AgentFlow to model inter-node NVLink and AWS NeuronLink transfer latency for large models.
How work is evaluated
Measures accuracy of predicted execution latency against baseline trace benchmarks across different tensor parallel topologies.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
Latency Accuracy Threshold
Error between predicted step time and ground truth must be <= 5%.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Prediction MAPE
Mean Absolute Percentage Error across cluster layouts. • target: 0.02 • range: 0-0.05
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Build a multi-agent interconnect simulation pipeline using Google ADK and AgentFlow.
Profile network communication bottlenecks (AllReduce, AllGather) across H100 and Trainium2 topologies.
Select optimal Tensor Parallelism (TP) and Pipeline Parallelism (PP) split schemes automatically.
Benchmark model execution against measured baseline latency curves.
Reference links and supporting material
Network interconnect bandwidth matrices and tensor shapes for 8-node H100 and Trainium2 clusters.
Challenge setup
Measures accuracy of predicted execution latency against baseline trace benchmarks across different tensor parallel topologies.
Challenge input
JSON containing model architecture and cluster topology
Google ADK
Agent development kit for building structured multi-agent workflows
AgentFlow
Coordinates agent task flow for complex system modeling
Evaluated output
JSON containing predicted step_time_ms and recommended_tp
- Error between predicted step time and ground truth must be <= 5%.
- Mean Absolute Percentage Error across cluster layouts. • target: 0.02 • range: 0-0.05
- Benchmark: Distributed LLM Network Benchmark
- Prediction MAPE target: 0.02
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.
View technical recipe
Configured tools
- AgentFlow · Required
- Google · Optional
- Google ADK · Optional
Evaluation contract
- Latency Accuracy Threshold · Weight 1
- Prediction MAPE · Weight 1
Metrics
- Prediction MAPE · Target 0.02
Benchmarks
- Distributed LLM Network Benchmark
- general
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON containing model architecture and cluster topology
Output: JSON containing predicted step_time_ms and recommended_tp
Execution harness: Python
Evaluation tools
- Google ADK · Agent Framework
- AgentFlow · Orchestration Tool
Recipe freeze marker
No recipe freeze time is recorded.