ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
  Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model                          |       size |     params | backend    | ngl | fa |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
/opt/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu:92: ROCm error
/usr/local/lib64/libggml-base.so.0(+0x3565) [0x7fd2c4f8e565]
/usr/local/lib64/libggml-base.so.0(ggml_print_backtrace+0x1eb) [0x7fd2c4f8e92b]
/usr/local/lib64/libggml-base.so.0(ggml_abort+0x11f) [0x7fd2c4f8eaaf]
/usr/local/lib64/libggml-hip.so.0(+0x300aef2) [0x7fd2c8055ef2]
/usr/local/lib64/libggml-hip.so.0(+0x30100fe) [0x7fd2c805b0fe]
/usr/local/lib64/libggml-base.so.0(ggml_backend_sched_synchronize+0x2e) [0x7fd2c4fa5a9e]
/usr/local/lib64/libllama.so.0(_ZN13llama_context11synchronizeEv+0x10) [0x7fd2c8722cf0]
/usr/local/bin/llama-bench() [0x40acfc]
/usr/local/bin/llama-bench() [0x408a7d]
/lib64/libc.so.6(+0x35b5) [0x7fd2c49245b5]
/lib64/libc.so.6(__libc_start_main+0x88) [0x7fd2c4924668]
/usr/local/bin/llama-bench() [0x409b65]
✖ ! [rocm7.1.1-mmf] Ministral-3-14B-Instruct-2512-BF16__fa1 failed (exit 0)