Replace ggml_mul_mat()->llm_build_lora_mm()

Author: suhara

src/llama.cpp

@@ -13861,14 +13861,14 @@ struct llm_build_context {
                     cb(Qcur, "Qcur", il);
                 }
 
-                struct ggml_tensor * Kcur = ggml_mul_mat(ctx0, model.layers[il].wk, cur);
+                struct ggml_tensor * Kcur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wk, cur);
                 cb(Kcur, "Kcur", il);
                 if (model.layers[il].bk) {
                     Kcur = ggml_add(ctx0, Kcur, model.layers[il].bk);
                     cb(Kcur, "Kcur", il);
                 }
 
-                struct ggml_tensor * Vcur = ggml_mul_mat(ctx0, model.layers[il].wv, cur);
+                struct ggml_tensor * Vcur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wv, cur);
                 cb(Vcur, "Vcur", il);
                 if (model.layers[il].bv) {
                     Vcur = ggml_add(ctx0, Vcur, model.layers[il].bv);
@@ -13937,7 +13937,7 @@ struct llm_build_context {
         cb(cur, "result_norm", -1);
 
         // lm_head
-        cur = ggml_mul_mat(ctx0, model.output, cur);
+        cur = llm_build_lora_mm(lctx, ctx0, model.output, cur);
         cb(cur, "result_output", -1);
 
         ggml_build_forward_expand(gf, cur);