Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

AMD顯卡無法被檢測到,皆是以CPU運行 #383

Closed
llamasensei7746 opened this issue Jul 2, 2023 · 14 comments
Closed

AMD顯卡無法被檢測到,皆是以CPU運行 #383

llamasensei7746 opened this issue Jul 2, 2023 · 14 comments

Comments

@llamasensei7746
Copy link

Issue Type

Question

vc client version number

MMVCServerSIO_win_onnxdirectML-cuda_v.1.5.3.7-001

OS

win10 21H2 19044.3086

GPU

RX6600

Clear setting

yes

Sample model

yes

Input chunk num

no

Wait for a while

The GUI successfully launched.

Voice Changer type

RVC

Model type

ONNX

Situation

I downloaded the directML version, but I can't run with gpu, when I start using cpu all run with cpu and used 90%
The sound became spike and the latency was very high
have confirmed that the rx6600 is supported by onnxruntime
The graphics card driver is also the latest, and supports directML
What is the solution?

btw,im using transtlator.

@w-okada
Copy link
Owner

w-okada commented Jul 2, 2023

How about gpu usage displayed in performance monitor?
Of course, not all processing runs on onnxruntime. If the usage of AMD GPUs is increasing, then onnxruntime dirctML should be working. The rest of the parts running outside of onnxruntime are making CPU usage go up. For example F0 estimation, retrieving features, or so.

@x1207349263
Copy link

same,my gpu is 6700xt and also run with my cpu.
image

@llamasensei7746
Copy link
Author

llamasensei7746 commented Jul 3, 2023

I tested
this is no running VC
https://media.discordapp.net/attachments/606063911896088581/1125330884539719760/image.png?width=731&height=676

This is running VC
https://cdn.discordapp.com/attachments/606063911896088581/1125331855755976824/image.png

Yes,it still using GPU but very low usage and make it so lagging

@w-okada
Copy link
Owner

w-okada commented Jul 4, 2023

Set index to zero. Processing index is very heavy.

@w-okada
Copy link
Owner

w-okada commented Jul 6, 2023

no res close

@w-okada w-okada closed this as completed Jul 6, 2023
@ProFFs
Copy link

ProFFs commented Jul 8, 2023

What the index? i have same problem

@Katze719
Copy link

Katze719 commented Jul 9, 2023

Issue is still there with index set to 0

@llamasensei7746
Copy link
Author

no res close

Sorry, I've been a little busy lately, even if I set it to 0, it's the same

@x1207349263
Copy link

x1207349263 commented Jul 9, 2023

no res close

Sorry, I've been a little busy lately, even if I set it to 0, it's the same

I upgraded the latest version and the max GPU load is about 30%.

@w-okada
Copy link
Owner

w-okada commented Jul 9, 2023

As I mention above, it's being processed by the GPU alone.

@dudostka228
Copy link

RX 580 is not included. please add it

@SankiruKun
Copy link

SankiruKun commented Mar 29, 2024

RX 580 в комплект не входит. Пожалуйста, добавьте его
still not added? (его еще не добавили?)

@StoneCentaur2
Copy link

I have an rx 5500 xt 8GB and it doesn't detect the gpu

@Kuuko-fokkusugaru
Copy link

I have an rx 5500 xt 8GB and it doesn't detect the gpu

Try v2 of RVC https://huggingface.co/wok000/vcclient000/tree/main

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

9 participants