Skip to content

GitLab

Commit fb9cdfa7 authored by Daniel Hiltgen's avatar Daniel Hiltgen
Browse files

Fix server.cpp for the new cuda build macros

parent efac4886
Show whitespace changes
Inline Side-by-side
Showing with 7 additions and 7 deletions
llm/ext_server/server.cpp
View file @ fb9cdfa7
...@@ -2335,9 +2335,9 @@ static void server_params_parse(int argc, char **argv, server_params &sparams, g ...@@ -2335,9 +2335,9 @@ static void server_params_parse(int argc, char **argv, server_params &sparams, g
invalid_param = true; invalid_param = true;
break; break;
} }
#ifndef GGML_USE_CUBLAS #ifndef GGML_USE_CUDA
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS. Setting the split mode has no effect.\n"); fprintf(stderr, "warning: llama.cpp was compiled without CUDA. Setting the split mode has no effect.\n");
#endif // GGML_USE_CUBLAS #endif // GGML_USE_CUDA
} }
else if (arg == "--tensor-split" || arg == "-ts") else if (arg == "--tensor-split" || arg == "-ts")
{ {
...@@ -2346,7 +2346,7 @@ static void server_params_parse(int argc, char **argv, server_params &sparams, g ...@@ -2346,7 +2346,7 @@ static void server_params_parse(int argc, char **argv, server_params &sparams, g
invalid_param = true; invalid_param = true;
break; break;
} }
#if defined(GGML_USE_CUBLAS) || defined(GGML_USE_SYCL) #if defined(GGML_USE_CUDA) || defined(GGML_USE_SYCL)
std::string arg_next = argv[i]; std::string arg_next = argv[i];
// split string by , and / // split string by , and /
...@@ -2367,8 +2367,8 @@ static void server_params_parse(int argc, char **argv, server_params &sparams, g ...@@ -2367,8 +2367,8 @@ static void server_params_parse(int argc, char **argv, server_params &sparams, g
} }
} }
#else #else
LOG_WARNING("llama.cpp was compiled without cuBLAS. It is not possible to set a tensor split.\n", {}); LOG_WARNING("llama.cpp was compiled without CUDA. It is not possible to set a tensor split.\n", {});
#endif // GGML_USE_CUBLAS #endif // GGML_USE_CUDA
} }
else if (arg == "--main-gpu" || arg == "-mg") else if (arg == "--main-gpu" || arg == "-mg")
{ {
...@@ -2377,7 +2377,7 @@ static void server_params_parse(int argc, char **argv, server_params &sparams, g ...@@ -2377,7 +2377,7 @@ static void server_params_parse(int argc, char **argv, server_params &sparams, g
invalid_param = true; invalid_param = true;
break; break;
} }
#if defined(GGML_USE_CUBLAS) || defined(GGML_USE_SYCL) #if defined(GGML_USE_CUDA) || defined(GGML_USE_SYCL)
params.main_gpu = std::stoi(argv[i]); params.main_gpu = std::stoi(argv[i]);
#else #else
LOG_WARNING("llama.cpp was compiled without cuBLAS. It is not possible to set a main GPU.", {}); LOG_WARNING("llama.cpp was compiled without cuBLAS. It is not possible to set a main GPU.", {});
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment