vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update llama_model_quantize_params

Browse source
This commit is contained in:
z5269887 2024-04-22 23:38:09 +08:00
parent d6e453eb6c
commit 141eb5107f
2 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama.cpp
View file

@ -14184,6 +14184,7 @@ struct llama_model_quantize_params llama_model_quantize_default_params() {
/*.quantize_output_tensor =*/ true, /*.quantize_output_tensor =*/ true,
/*.only_copy =*/ false, /*.only_copy =*/ false,
/*.pure =*/ false, /*.pure =*/ false,
/*.keep_split =*/ false,
/*.imatrix =*/ nullptr, /*.imatrix =*/ nullptr,
/*.kv_overrides =*/ nullptr, /*.kv_overrides =*/ nullptr,
}; };

2
llama.h
View file

@ -288,9 +288,9 @@ extern "C" {
bool quantize_output_tensor; // quantize output.weight bool quantize_output_tensor; // quantize output.weight
bool only_copy; // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored 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 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 * imatrix; // pointer to importance matrix data
void * kv_overrides; // pointer to vector containing overrides void * kv_overrides; // pointer to vector containing overrides
bool keep_split; // quantize to the same number of shards
} llama_model_quantize_params; } llama_model_quantize_params;
// grammar types // grammar types