RVC-Project/Retrieval-based-Voice-Conversion

Api not releasing memory after inference

Open

#6 opened on Jan 26, 2024

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Python (126 forks)auto 404
bugenhancementhelp wanted

Repository metrics

Stars
 (591 stars)
PR merge metrics
 (PR metrics pending)

Description

Hi there,

I believe I almost have this all figured out and it's working great. One issue I'm having is that after infering one time using the API, memory usage stays very high (12.7gb out of 16), even though no processing is happening. This is happening on a macbook air m1 16gb. Is there a way to force rvc to release that memory usage after each api call? Thanks in advance!

Contributor guide

Research direction
Profile memory usage after API inference. Check if model tensors or caches are not being released. Consider explicitly deleting variables and calling garbage collection. Investigate if there is a global variable holding references to the model.
Tech stack
python
Domain
apimachine learning
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
Pythonmemory profiling
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40