ci : add windows-cuda 13.1 release

[CISC]

Add CUDA 13.1 release.

Successful run: https://github.com/CISC/llama.cpp/actions/runs/19998436189/job/57349842014
Release: https://github.com/CISC/llama.cpp/releases/tag/b7313

Note

Interestingly the ggml-cuda.dll is a fraction of the size of 12.4 release, not entirely sure why, haven't tested it either.

[am17an]

I think it is because they drop support for older architectures

[CISC]

Can anyone confirm the release binaries work?

[fuutott]

D:\llama>d:/llama/latest/llama-bench.exe   -m d:\models\lmstudio-community\gpt-oss-120b-GGUF\gpt-oss-120b-MXFP4-00001-of-00002.gguf   -p 512   -n 512   -b 1024   -ub 512   -ngl 99  -mmp 0   -fa 1   -o md   -r 3   -d 0
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA RTX PRO 6000 Blackwell Workstation Edition, compute capability 12.0, VMM: yes
load_backend: loaded CUDA backend from d:\llama\latest\ggml-cuda.dll
load_backend: loaded RPC backend from d:\llama\latest\ggml-rpc.dll
load_backend: loaded CPU backend from d:\llama\latest\ggml-cpu-sapphirerapids.dll
| model                          |       size |     params | backend    | ngl | n_batch | fa | mmap |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ------: | -: | ---: | --------------: | -------------------: |
| gpt-oss 120B MXFP4 MoE         |  59.02 GiB |   116.83 B | CUDA       |  99 |    1024 |  1 |    0 |           pp512 |     4718.55 ± 125.71 |
| gpt-oss 120B MXFP4 MoE         |  59.02 GiB |   116.83 B | CUDA       |  99 |    1024 |  1 |    0 |           tg512 |        237.14 ± 1.22 |

build: 80acf82d (7313)