RVC-Project / RVC-Project/Retrieval-based-Voice-Conversion-WebUI

CUDNN

Open
#2,812 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
38.4k
Forks
5.3k
PR merge metrics
No merged PRs in 30d

Description

How can it be that when I have to do an inference over 16 min. I have to turn off CUDNN with the following code: torch.backends.cudnn.enabled = False` I am uusing a rtx 4080 and i will upgrade to my rtx 5090 i am using rvc rtx 5090 version.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No file, test, or entry point is named. Start by reproducing the reported inference delay with torch.backends.cudnn.enabled set both ways on the stated RTX setup, then trace the inference path to identify where CUDNN changes behavior. Done means the cause and a reproducible expected behavior are established.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.