llama-quant : fix `--tensor-type` when default `qtype` is overriden (#22572)

fix #22544 (my fault!)

Credit to @Anai-Guo, ref #22559 - since that one was closed due to the
new contributor policy I am taking the liberty of re-submitting that PR
here.

diff --git a/src/llama-quant.cpp b/src/llama-quant.cpp
index 25a333b4a7f12a7964d24a4cee89b138973806ed..2f0f70b73b6cc0322bbee3fa59a72d98ebc45885 100644 (file)
--- a/src/llama-quant.cpp
+++ b/src/llama-quant.cpp
@@ -683,9 +683,9 @@ static ggml_type llama_tensor_get_type(quantize_state_impl & qs, const llama_mod
                         LLAMA_LOG_WARN("%s: %-36s - applying manual override: %s -> %s\n",
                                        __func__, tensor_name.c_str(), ggml_type_name(new_type), ggml_type_name(qtype));
                         new_type = qtype;
-                        manual = true;
-                        break;
                     }
+                    manual = true;
+                    break;
                 }
             }
         }