diff options
Diffstat (limited to 'llama.h')
-rw-r--r-- | llama.h | 1 |
1 files changed, 1 insertions, 0 deletions
@@ -288,6 +288,7 @@ extern "C" { bool quantize_output_tensor; // quantize output.weight 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 void * imatrix; // pointer to importance matrix data void * kv_overrides; // pointer to vector containing overrides } llama_model_quantize_params; |