SAGE Control Plane Benchmark Report

{{ subtitle | default('Scheduling Policy Performance Analysis') }}

Summary

{% if best_throughput %}

Best Throughput

{{ best_throughput_value }} req/s
{{ best_throughput }}
{% endif %} {% if best_slo_compliance %}

Best SLO Compliance

{{ best_slo_value }}%
{{ best_slo_compliance }}
{% endif %} {% if best_p99_latency %}

Best P99 Latency

{{ best_p99_value }} ms
{{ best_p99_latency }}
{% endif %}

Configuration

{{ config.control_plane_url }}
{{ config.num_requests }}
{{ config.request_rate }} req/s
{{ config.arrival_pattern }}
{{ config.policies | join(', ') }}
{{ config.warmup_requests }}

Policy Comparison

{% for policy_name, result in policy_results.items() %} {% endfor %}
Policy Throughput Avg Latency P99 Latency Avg TTFT SLO Compliance Error Rate
{{ policy_name }} {{ "%.1f"|format(result.metrics.throughput_rps) }} req/s {{ "%.0f"|format(result.metrics.e2e_latency_avg_ms) }} ms {{ "%.0f"|format(result.metrics.e2e_latency_p99_ms) }} ms {{ "%.0f"|format(result.metrics.ttft_avg_ms) }} ms {{ "%.1f"|format(result.metrics.slo_compliance_rate * 100) }}% {{ "%.1f"|format(result.metrics.error_rate * 100) }}%
{% if charts %}

Performance Charts

{% for chart in charts %}
{{ chart.title }}

{{ chart.title }}

{% endfor %}
{% endif %}

Detailed Results

{% for policy_name, result in policy_results.items() %}
{{ policy_name }} {{ "%.1f"|format(result.metrics.slo_compliance_rate * 100) }}% SLO

Throughput

Request Throughput
{{ "%.1f"|format(result.metrics.throughput_rps) }}
req/s
Token Throughput
{{ "%.1f"|format(result.metrics.token_throughput_tps) }}
tokens/s
Duration
{{ "%.1f"|format(result.metrics.duration_seconds) }}
seconds

Latency

E2E Average
{{ "%.0f"|format(result.metrics.e2e_latency_avg_ms) }}
ms
E2E P50
{{ "%.0f"|format(result.metrics.e2e_latency_p50_ms) }}
ms
E2E P95
{{ "%.0f"|format(result.metrics.e2e_latency_p95_ms) }}
ms
E2E P99
{{ "%.0f"|format(result.metrics.e2e_latency_p99_ms) }}
ms
TTFT Average
{{ "%.0f"|format(result.metrics.ttft_avg_ms) }}
ms
TBT Average
{{ "%.1f"|format(result.metrics.tbt_avg_ms) }}
ms

Request Statistics

Total
{{ result.metrics.total_requests }}
Completed
{{ result.metrics.completed_requests }}
Failed
{{ result.metrics.failed_requests }}
Timeouts
{{ result.metrics.timeout_requests }}
{% endfor %}