q2_K: allow it to detect ternary nets and quantize accordingly

1 files changed, 1 insertions, 0 deletions

diff --git a/include/llama.h b/include/llama.h
index 88d82958..15ff915b 100644
--- a/include/llama.h
+++ b/include/llama.h
@@ -359,6 +359,7 @@ 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
         bool keep_split;                     // quantize to the same number of shards
+        bool ignore_imatrix_rules;           // If set to true, the built-in rules for refusing to quantize into certain quants without imatrix are ignored
         void * imatrix;                      // pointer to importance matrix data
         void * kv_overrides;                 // pointer to vector containing overrides
     } llama_model_quantize_params;