diff options
Diffstat (limited to 'common/common.cpp')
| -rw-r--r-- | common/common.cpp | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/common/common.cpp b/common/common.cpp index 53002ba3..ff19ec4e 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -613,9 +613,11 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) { fprintf(stdout, " how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n"); fprintf(stdout, " -mg i, --main-gpu i the GPU to use for scratch and small tensors\n"); fprintf(stdout, " -lv, --low-vram don't allocate VRAM scratch buffer\n"); +#ifdef GGML_USE_CUBLAS fprintf(stdout, " -nommq, --no-mul-mat-q\n"); - fprintf(stdout, " use cuBLAS instead of custom mul_mat_q CUDA kernels.\n"); + fprintf(stdout, " use " GGML_CUBLAS_NAME " instead of custom mul_mat_q " GGML_CUDA_NAME " kernels.\n"); fprintf(stdout, " Not recommended since this is both slower and uses more VRAM.\n"); +#endif // GGML_USE_CUBLAS #endif fprintf(stdout, " --mtest compute maximum memory usage\n"); fprintf(stdout, " --export export the computation graph to 'llama.ggml'\n"); |