RVC-Project / RVC-Project/Retrieval-based-Voice-Conversion-WebUI
是否可以支持 i卡 oneapi的方式
Open
Nobody has claimed this yet.
todo list
- Dominant language
- Python
- Stars
- 38.4k
- Forks
- 5.3k
- PR merge metrics
- No merged PRs in 30d
Description
我的显卡是A770，在ai绘图中使用oneapi的 性能要比dml好上不少
oneapi的方式在sd中已经验证可行，请问是否能获取支持
下面是这是sd.next里做hijack的例子
https://github.com/vladmandic/automatic/blob/84456740b06490ffab39e0773ea6d1683b6f9784/modules/ipex_specific/__init__.py#L101
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the linked SD.next example in modules/ipex_specific/init.py around line 101 and compare its oneAPI hijack approach with this project’s current DML-based GPU support. Define the scope of Intel oneAPI support for the A770 and verify that the voice-conversion workflow works with the new backend.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100