25 Commits

Author SHA1 Message Date
google-labs-jules[bot]
d3b8f7e09e feat: Migrate from CUDA to XPU for Intel GPU support
This commit migrates the project from using NVIDIA CUDA to Intel XPU for GPU acceleration, based on the PyTorch 2.9 release.

Key changes include:
- Replaced `torch.cuda` with `torch.xpu` for device checks, memory management, and distributed training.
- Updated device strings from "cuda" to "xpu" across the codebase.
- Switched the distributed training backend from "nccl" to "ccl" for Intel GPUs.
- Disabled custom CUDA kernels in the `BigVGAN` module by setting `use_cuda_kernel=False`.
- Updated `requirements.txt` to include `torch==2.9` and `intel-extension-for-pytorch`.
- Modified CI/CD pipelines and build scripts to remove CUDA dependencies and build for an XPU target.
2025-11-10 13:09:27 +00:00
XXXXRT666
6fdc67ca83
Fix bugs in install.sh, reduce log noise, and improve error reporting (#2464)
* Update Install.sh

* Format Code

* Delete dev null

* Update README, Support Dark Mode in CSS/JS
2025-06-17 15:21:36 +08:00
RVC-Boss
7d70852a3f
fix precision auto detection
fix precision auto detection
2025-06-05 18:27:53 +08:00
XXXXRT666
05d44215f1
Make Pre-Commit-Hook Exit 0 While Using Ruff Check (#2427)
Modified gradio Layout
Refactor WebUI half-precision and GPU detection logic
2025-06-05 10:46:05 +08:00
SapphireLab
2ff2cf5ba1
fix(config): Fix errors when running inference webui directly (#2426) 2025-06-05 00:26:44 +08:00
RVC-Boss
f4ac9123af
support sovits v2Pro v2ProPlus
support sovits v2Pro v2ProPlus
2025-06-04 15:25:22 +08:00
RVC-Boss
68cae3fa10
support sovits v2Pro v2ProPlus
support sovits v2Pro v2ProPlus
2025-06-04 15:24:29 +08:00
RVC-Boss
b7c0c5ca87
support sovits v2Pro v2ProPlus
support sovits v2Pro v2ProPlus
2025-06-04 15:15:54 +08:00
XXXXRT666
53cac93589
Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)
* ruff check --fix

* ruff format --line-length 120 --target-version py39

* Change the link for G2PW Model

* update pytorch version and colab
2025-04-07 16:42:47 +08:00
XXXXRT666
db40317d9c
Update config.py
精简代码
2024-02-21 01:15:31 +00:00
XXXXRT666
3180294710
Update config.py
Change the inference device for Mac to accelerate inference and reduce memory leak
2024-02-20 15:57:58 +00:00
Kenn Zhang
3857c7d15b 新增is_share参数也从环境变量中获取;更改is_half/is_share从环境变量中获取值的方式。 2024-02-13 03:14:01 +00:00
YuChuXi
a0af8c32de config.py :
现在在检查半精度计算前会先检查CUDA
webui.py :
  优化users.py的写入
2024-01-27 14:11:10 +08:00
RVC-Boss
6f1b4fd756
Update config.py 2024-01-26 18:59:34 +08:00
RVC-Boss
84ee471936
Add files via upload 2024-01-26 18:11:09 +08:00
Wu Zichen
07a5339691 mps support 2024-01-24 19:37:47 +08:00
Wu Zichen
382102c9d0 mps support, optimized device selection 2024-01-24 16:45:13 +08:00
RVC-Boss
d1ec88193f
Update config.py 2024-01-23 18:41:05 +08:00
Kenn Zhang
d96b7d65ec Docker化初步版本完成 2024-01-23 17:00:31 +08:00
RVC-Boss
f61471166c
Add files via upload 2024-01-21 23:02:13 +08:00
Miuzarte
21b9c20fc8 config.py引入class, requirement补全, 自述追加已测试环境 2024-01-20 14:15:02 +08:00
謬紗特
18c3907682
Update config.py 2024-01-19 14:25:15 +08:00
RVC-Boss
318ebe5d9f
Update config.py 2024-01-17 16:17:43 +08:00
RVC-Boss
bac65693c6
Update config.py 2024-01-17 16:17:34 +08:00
RVC-Boss
56516fe619
Add files via upload 2024-01-16 17:25:53 +08:00