⚡ Bolt: Cache ML models in memory to improve processing speed - #237
⚡ Bolt: Cache ML models in memory to improve processing speed#237benpiper wants to merge 1 commit into
Conversation
Added `@functools.lru_cache(maxsize=1)` to `_load_whisper_model` in `processor.py` and `load_rvm_model` in `background_remover.py` to cache instantiated ML models in memory globally. This prevents repeated disk loading during subsequent processing runs, significantly improving performance while avoiding Out-Of-Memory (OOM) issues. 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)to_load_whisper_modelinprocessor.pyandload_rvm_modelinbackground_remover.py.Why: Repeatedly loading large ML models from disk on every processing run creates a severe performance bottleneck.
Impact: Dramatically reduces initialization time for subsequent processing requests using the same models.
Measurement: Time the loading sequence of models. The first load takes full time, subsequent loads take ~0.00s.
PR created automatically by Jules for task 17999459642173618568 started by @benpiper