🧪 [Testing Improvement] Add edge cases testing to Engine.greedyNextToken#29
🧪 [Testing Improvement] Add edge cases testing to Engine.greedyNextToken#29
Conversation
Added tests for edge cases to cover negative numbers, duplicate entries, and duplicates at the maximum entry point to ensure Engine.greedyNextToken returns the correct index according to the specifications. Evaluated test behavior using an initialized `eng.logits` array to avoid uninitialized `f32` memory values from disrupting test comparisons. Co-authored-by: ulac000000 <132948319+ulac000000@users.noreply.github.com>
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
1 participant
🎯 What: The testing gap addressed is the lack of coverage for
Engine.greedyNextTokenspecific to edge case logic.📊 Coverage: The function is now tested for three key scenarios: Negative logit values handling, ties (arrays with equivalent entries uniformly), and duplicates in maximums.
✨ Result: The
greedyNextTokenlogic is fully verified across standard and edge case distributions ensuring predictable and reliable deterministic sampling during decoding.PR created automatically by Jules for task 6463341012523233563 started by @ulac000000