Python bindings don't recognize my GPU

[yuhlearn]

Hello!

I have tried a lot of C++ projects that use ncnn with great success and without any issues (thank you!). However, I would like to use Python bindings for my own project and discovered that I can't get them to recognize my GPU.

I have tried the bindings provided by this project, installed with pip, compiled various projects found on github that provide their own bindings for their ncnn projects, as well as created my own bindings with both Pybind11 and SWIG. Every time I get the same result:

Instead of finding all available GPU devices

[0 AMD Radeon RX 460 Graphics (RADV POLARIS11)]  queueC=1[4]  queueG=0[1]  queueT=0[1]
[0 AMD Radeon RX 460 Graphics (RADV POLARIS11)]  bugsbn1=0  bugbilz=0  bugcopc=0  bugihfa=0
[0 AMD Radeon RX 460 Graphics (RADV POLARIS11)]  fp16-p/s/a=1/1/0  int8-p/s/a=1/1/1
[0 AMD Radeon RX 460 Graphics (RADV POLARIS11)]  subgroup=64  basic=1  vote=1  ballot=1  shuffle=1
[1 Intel(R) HD Graphics 4000 (IVB GT2)]  queueC=0[1]  queueG=0[1]  queueT=0[1]
[1 Intel(R) HD Graphics 4000 (IVB GT2)]  bugsbn1=0  bugbilz=0  bugcopc=0  bugihfa=0
[1 Intel(R) HD Graphics 4000 (IVB GT2)]  fp16-p/s/a=1/0/0  int8-p/s/a=1/0/0
[1 Intel(R) HD Graphics 4000 (IVB GT2)]  subgroup=32  basic=1  vote=1  ballot=1  shuffle=1
[2 llvmpipe (LLVM 15.0.6, 256 bits)]  queueC=0[1]  queueG=0[1]  queueT=0[1]
[2 llvmpipe (LLVM 15.0.6, 256 bits)]  bugsbn1=0  bugbilz=0  bugcopc=0  bugihfa=0
[2 llvmpipe (LLVM 15.0.6, 256 bits)]  fp16-p/s/a=1/1/1  int8-p/s/a=1/1/1
[2 llvmpipe (LLVM 15.0.6, 256 bits)]  subgroup=8  basic=1  vote=1  ballot=1  shuffle=1

ncnn will only find the integrated Intel device

[0 Intel(R) HD Graphics 4000 (IVB GT2)]  queueC=0[1]  queueG=0[1]  queueT=0[1]
[0 Intel(R) HD Graphics 4000 (IVB GT2)]  bugsbn1=0  bugbilz=49  bugcopc=0  bugihfa=0
[0 Intel(R) HD Graphics 4000 (IVB GT2)]  fp16-p/s/a=1/0/0  int8-p/s/a=1/0/0
[0 Intel(R) HD Graphics 4000 (IVB GT2)]  subgroup=32  basic=1  vote=1  ballot=1  shuffle=1

This happens every time I use ncnn through Python.

I'm trying to understand why this happens and if there is a solution to this problem. Any insight would be appreciated!