diff options
Diffstat (limited to 'examples/llava')
| -rw-r--r-- | examples/llava/MobileVLM-README.md | 2 | ||||
| -rw-r--r-- | examples/llava/clip.cpp | 4 |
2 files changed, 3 insertions, 3 deletions
diff --git a/examples/llava/MobileVLM-README.md b/examples/llava/MobileVLM-README.md index 4d5fef02..b3b66331 100644 --- a/examples/llava/MobileVLM-README.md +++ b/examples/llava/MobileVLM-README.md @@ -124,7 +124,7 @@ llama_print_timings: total time = 34570.79 ms ## Orin compile and run ### compile ```sh -make LLAMA_CUBLAS=1 CUDA_DOCKER_ARCH=sm_87 LLAMA_CUDA_F16=1 -j 32 +make LLAMA_CUDA=1 CUDA_DOCKER_ARCH=sm_87 LLAMA_CUDA_F16=1 -j 32 ``` ### run on Orin diff --git a/examples/llava/clip.cpp b/examples/llava/clip.cpp index 48caafa8..40c97626 100644 --- a/examples/llava/clip.cpp +++ b/examples/llava/clip.cpp @@ -7,7 +7,7 @@ #include "ggml-alloc.h" #include "ggml-backend.h" -#ifdef GGML_USE_CUBLAS +#ifdef GGML_USE_CUDA #include "ggml-cuda.h" #endif @@ -968,7 +968,7 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) { } } -#ifdef GGML_USE_CUBLAS +#ifdef GGML_USE_CUDA new_clip->backend = ggml_backend_cuda_init(0); printf("%s: CLIP using CUDA backend\n", __func__); #endif |