quantize : be able to override metadata by key (#6321)

* quantize: be able to override metadata by key

* minor : spacing

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

1 files changed, 1 insertions, 0 deletions

diff --git a/llama.h b/llama.h
index 74f0e56d..6daf3a35 100644
--- a/llama.h
+++ b/llama.h
@@ -284,6 +284,7 @@ extern "C" {
         bool only_copy;                      // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored
         bool pure;                           // quantize all tensors to the default type
         void * imatrix;                      // pointer to importance matrix data
+        void * kv_overrides;                 // pointer to vector containing overrides
     } llama_model_quantize_params;
 
     // grammar types