happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add use_wce option

This commit is contained in:
Ed Addario 2026-01-21 18:26:58 +00:00
parent 0b63f50463
commit 25d7ecc42a
No known key found for this signature in database
GPG Key ID: E7875815A3230993
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
include/llama.h
View File

@ -391,6 +391,7 @@ extern "C" {
bool keep_split; // quantize to the same number of shards
void * imatrix; // pointer to importance matrix data
void * activations; // pointer to activations data
void * statistics; // pointer to statistics data
void * kv_overrides; // pointer to vector containing overrides
void * tensor_types; // pointer to vector containing tensor types
void * prune_layers; // pointer to vector containing layer indices to prune
@ -399,6 +400,7 @@ extern "C" {
bool save_state; // keep bpw state file
void * state_file; // pointer to bpw state file
bool ignore_tensor_importance; // allocate target bpw budget equitably across all tensors
bool use_wce; // optimize for WCE instead of MSE
} llama_model_quantize_params;
typedef struct llama_logit_bias {