⚡ Bolt: Cache large ML models globally - #248
Conversation
Added `functools.lru_cache(maxsize=1)` to `whisper.load_model` wrapper and `load_rvm_model`. Instantiating large ML models repeatedly causes severe performance bottlenecks from disk loading and risks Out-Of-Memory (OOM) errors. Eliminates redundant model loading from disk, significantly speeding up consecutive video processing requests. Co-authored-by: benpiper <4343814+benpiper@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: Added
functools.lru_cache(maxsize=1)towhisper.load_modelwrapper andload_rvm_model.🎯 Why: Instantiating large ML models repeatedly causes severe performance bottlenecks from disk loading and risks Out-Of-Memory (OOM) errors.
📊 Impact: Eliminates redundant model loading from disk, significantly speeding up consecutive video processing requests.
🔬 Measurement: Run a test video processing and observe the logs. The first request will load the model, while subsequent requests will retrieve the model instantly from memory.
PR created automatically by Jules for task 2408165040206565149 started by @benpiper