Distribute and run LLMs with a single file.
C++ cross-platformggufllama-cpplocal-ailocal-inferencelocal-llmopen-source-aisingle-file-executablespeech-to-text
Disable GPU in llava-quantize
Justine Tunneyea2a96e5bf82
diff --git a/llama.cpp/llava/llava-quantize.cpp b/llama.cpp/llava/llava-quantize.cppindex 2be15c88..41ec02f1 100644--- a/llama.cpp/llava/llava-quantize.cpp+++ b/llama.cpp/llava/llava-quantize.cpp@@ -10,6 +10,8 @@int main(int argc, char *argv[]) {+ FLAG_gpu = LLAMAFILE_GPU_DISABLE; // [jart]+if (llamafile_has(argv, "--version")) {puts("llava-quantize v" LLAMAFILE_VERSION_STRING);return 0;