quantize : handle user-defined pruning of whole layers (blocks) (#13037)

This commit is contained in:
Ed Addario authored and GitHub committed 2025-06-22 23:16:26 +02:00
1 parent 238005c2dc
commit fa4a9f2a1c
3 files changed
+119 -9

No files matched your search

+1
View File
@@ -390,6 +390,7 @@ extern "C" {
void * imatrix; // pointer to importance matrix 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
} llama_model_quantize_params;
typedef struct llama_logit_bias {