Distribute and run LLMs with a single file.
C++ cross-platformggufllama-cpplocal-ailocal-inferencelocal-llmopen-source-aisingle-file-executablespeech-to-text
Use LLAMAFILE_GPU_ERROR value -2 instead of -1 (#291)
Antonis Makropoulos70c7863dd1b6
diff --git a/llama.cpp/server/server.cpp b/llama.cpp/server/server.cppindex f1a65691..345b92c7 100644--- a/llama.cpp/server/server.cpp+++ b/llama.cpp/server/server.cpp@@ -2516,7 +2516,7 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,break;}FLAG_gpu = llamafile_gpu_parse(argv[i]);- if (FLAG_gpu == -1)+ if (FLAG_gpu == -2){fprintf(stderr, "error: invalid --gpu flag value: %s\n", argv[i]);exit(1);