ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
| model                          |       size |     params | backend    | ngl | fa | mmap |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
/opt/llama.cpp/ggml/src/ggml-rpc/ggml-rpc.cpp:690: Remote RPC server crashed or returned malformed response
/lib64/libggml-base.so.0(+0x3565) [0x7f5d2cbe9565]
/lib64/libggml-base.so.0(ggml_print_backtrace+0x1eb) [0x7f5d2cbe992b]
/lib64/libggml-base.so.0(ggml_abort+0x11f) [0x7f5d2cbe9aaf]
/lib64/libggml-rpc.so.0(+0x452a) [0x7f5d2fb8252a]
/lib64/libggml-base.so.0(+0x16232) [0x7f5d2cbfc232]
/lib64/libggml-base.so.0(ggml_backend_alloc_ctx_tensors_from_buft+0xff) [0x7f5d2cbfdf1f]
/lib64/libllama.so.0(_ZN11llama_model12load_tensorsER18llama_model_loader+0x3a26) [0x7f5d2fdaad06]
/lib64/libllama.so.0(+0x1cf16) [0x7f5d2fd11f16]
/lib64/libllama.so.0(llama_model_load_from_file+0xac) [0x7f5d2fd12d7c]
/usr/sbin/llama-bench() [0x406d85]
/lib64/libc.so.6(+0x35b5) [0x7f5d2c57f5b5]
/lib64/libc.so.6(__libc_start_main+0x88) [0x7f5d2c57f668]
/usr/sbin/llama-bench() [0x409255]