fix trailing whitespace

Author: ymcki

src/llama.cpp

@@ -7763,7 +7763,7 @@ static bool llm_load_tensors(
                     // output
                     model.output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
                     model.output      = create_tensor(tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab}, llama_model_loader::TENSOR_NOT_REQUIRED);
-                
+
                     // if output is NULL, init from the input tok embed
                     if (model.output == NULL) {
                         model.output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, llama_model_loader::TENSOR_DUPLICATED);
@@ -11029,19 +11029,19 @@ struct llm_build_context {
 
     struct ggml_cgraph * build_deci() {
         struct ggml_cgraph * gf = ggml_new_graph_custom(ctx0, llama_model_max_nodes(model), false);
-          
+
         // mutable variable, needed during the last layer of the computation to skip unused tokens
         int32_t n_tokens = this->n_tokens;
-        
+
         const int64_t n_embd_head = hparams.n_embd_head_v;
         GGML_ASSERT(n_embd_head == hparams.n_embd_head_k);
         GGML_ASSERT(n_embd_head == hparams.n_rot);
-        
+
         struct ggml_tensor * cur;
         struct ggml_tensor * inpL;
 
         inpL = llm_build_inp_embd(ctx0, lctx, hparams, ubatch, model.tok_embd, cb);
-            
+
         // inp_pos - contains the positions
         struct ggml_tensor * inp_pos = build_inp_pos();