Skip to content

test: Increase E2E load test token counts to 1500/1500 - #550

Closed
clubanderson wants to merge 1 commit into
mainfrom
fix/e2e-token-config
Closed

test: Increase E2E load test token counts to 1500/1500#550
clubanderson wants to merge 1 commit into
mainfrom
fix/e2e-token-config

Conversation

@clubanderson

Copy link
Copy Markdown
Contributor

Summary

  • Increase input and output token counts from 64 to 1500 for E2E load tests
  • Makes tests more realistic by simulating longer LLM inference requests
  • Helps better test EPP routing behavior under load

Changes

  • inputTokens: 64 → 1500
  • outputTokens: 64 → 1500

Rationale

With 64 tokens, requests complete very quickly, making it harder to:

  • Build up meaningful queue depth
  • Observe EPP routing decisions under sustained load
  • Test KV cache utilization patterns

1500 tokens better simulates production inference workloads.

Test plan

  • Run OpenShift E2E tests with new token configuration
  • Verify load generation works correctly with longer requests
  • Confirm scale-up behavior under sustained load

🤖 Generated with Claude Code

Increase input and output token counts from 64 to 1500 to make E2E
load tests more realistic. This change:

- Makes requests take longer, building queue faster
- Increases KV cache utilization to realistic levels
- Gives EPP more time to observe and react to queue imbalances
- Better simulates production LLM inference workloads

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Copilot AI review requested due to automatic review settings January 8, 2026 20:26

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR increases the token counts used in E2E load tests to better simulate production workloads and test EPP routing behavior under sustained load. The change updates both input and output token constants from 64 to 1500 tokens.

Key Changes:

  • Updated token configuration to use 1500 tokens (input and output) instead of 64
  • Enables more realistic load testing scenarios with longer-running requests

Comment thread test/e2e/e2e_test.go
outputTokens = 64
inputTokens = 1500
outputTokens = 1500
maxExecutionTimeSec = 600

Copilot AI Jan 8, 2026

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

With token counts increasing from 64 to 1500 (23x increase), the current 600-second timeout may be insufficient for tests to complete, especially under load conditions. Consider increasing maxExecutionTimeSec proportionally to account for longer inference times with 1500 tokens.

Suggested change
maxExecutionTimeSec = 600
maxExecutionTimeSec = 14400

Copilot uses AI. Check for mistakes.
@clubanderson
clubanderson deleted the fix/e2e-token-config branch January 8, 2026 20:27
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants