Add support for blackwell and Cuda 13.3 for the cuda build

Use case

Fix the issue with:
https://github.com/modelscope/FunASR/issues/3289

Implemented the fix for:
Cuda implementation broken

C:\Users\USER\Downloads\funasr-llamacpp-windows-x64-cuda>llama-funasr-sensevoice.exe -m sensevoice-small-q8.gguf -a sample.wav --backend cuda
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 16310 MiB):
  Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 16310 MiB

C:\Users\USER\Downloads\funasr-llamacpp-windows-x64-cuda>dir sample.wav
 Volume in drive C has no label.
 Volume Serial Number is ---

 Directory of C:\Users\USER\Downloads\funasr-llamacpp-windows-x64-cuda

07/19/2026  05:15 AM         1,077,326 sample.wav
               1 File(s)      1,077,326 bytes
               0 Dir(s)  89,731,526,656 bytes free

C:\Users\USER\Downloads\funasr-llamacpp-windows-x64-cuda>

C:\Users\USER\Downloads\funasr-llamacpp-windows-x64-cuda>llama-funasr-sensevoice.exe -m sensevoice-small-q8.gguf -a sample.wav
I'll record myself in English, no, you don't want.
[sensevoice] done 1.55s

Proposed solution

Add support for this card and cuda version!

Alternatives or workarounds

None

Expected impact

Improve performance for cuda

Start by reproducing the shown Windows executable command with the CUDA backend on the NVIDIA GeForce RTX 5060 Ti, then inspect the repository's CUDA build entry points. Done means the CUDA build supports Blackwell and CUDA 13.3 and the reported inference failure no longer occurs.