Distribute and run LLMs with a single file.
C++ cross-platformggufllama-cpplocal-ailocal-inferencelocal-llmopen-source-aisingle-file-executablespeech-to-text
Fix error with Apple Metal GPU compile
Justine Tunney1d8617ffed6f
diff --git a/llama.cpp/ggml-metal.m b/llama.cpp/ggml-metal.mindex 266b109a..40f09404 100644--- a/llama.cpp/ggml-metal.m+++ b/llama.cpp/ggml-metal.m@@ -1242,7 +1242,7 @@ void ggml_metal_graph_compute(}if (!ggml_metal_supports_op(dst)) {- GGML_METAL_LOG_ERROR("%s: error: unsupported op '%s'\n", __func__, ggml_op_desc(dst));+ GGML_METAL_LOG_ERROR("%s: error: unsupported op '%d'\n", __func__, dst->op);GGML_ASSERT(!"unsupported op");}