Merge branch 'ggerganov:master' into master

Author: apicalshark

examples/server/server.cpp

@@ -1090,22 +1090,21 @@ struct server_context {
             size_t pos = std::min(slot.n_sent_text, slot.generated_text.size());
 
             const std::string str_test = slot.generated_text.substr(pos);
-            bool is_stop_full = false;
+            bool send_text = true;
 
             size_t stop_pos = slot.find_stopping_strings(str_test, token_str.size(), STOP_TYPE_FULL);
             if (stop_pos != std::string::npos) {
-                is_stop_full = true;
                 slot.generated_text.erase(
                     slot.generated_text.begin() + pos + stop_pos,
                     slot.generated_text.end());
                 pos = std::min(slot.n_sent_text, slot.generated_text.size());
-            } else {
-                is_stop_full = false;
+            } else if (slot.has_next_token) {
                 stop_pos = slot.find_stopping_strings(str_test, token_str.size(), STOP_TYPE_PARTIAL);
+                send_text = stop_pos == std::string::npos;
             }
 
             // check if there is any token to predict
-            if (stop_pos == std::string::npos || (!slot.has_next_token && !is_stop_full && stop_pos > 0)) {
+            if (send_text) {
                 // no send the stop word in the response
                 result.text_to_send = slot.generated_text.substr(pos, std::string::npos);
                 slot.n_sent_text += result.text_to_send.size();

ggml/src/ggml-alloc.c

@@ -348,7 +348,6 @@ struct tensor_alloc {
 };
 
 struct leaf_alloc {
-    int buffer_id;
     struct tensor_alloc leaf;
 };
 
@@ -740,7 +739,6 @@ bool ggml_gallocr_reserve_n(ggml_gallocr_t galloc, struct ggml_cgraph * graph, c
     for (int i = 0; i < graph->n_leafs; i++) {
         struct ggml_tensor * leaf = graph->leafs[i];
         struct hash_node * hn = ggml_gallocr_hash_get(galloc, leaf);
-        galloc->leaf_allocs[i].buffer_id = hn->buffer_id;
         if (leaf->view_src || leaf->data) {
             galloc->leaf_allocs[i].leaf.buffer_id = -1;
             galloc->leaf_allocs[i].leaf.offset = SIZE_MAX;

scripts/sync-ggml.last

@@ -1 +1 @@
-564f42082f858f9674b2a2e06e9e779d9ed2c754
+2327bda7a55ac6b72614ac5ebd5c5a5e02553b9b

src/llama.cpp

@@ -16095,9 +16095,11 @@ struct llm_build_context {
         cur = ggml_get_rows(ctx0, cur, inp_out_ids);
 
         cur = llm_build_norm(ctx0, cur, hparams, model.output_norm, model.output_norm_b, LLM_NORM, cb, -1);
-        cur = llm_build_lora_mm(lctx, ctx0, model.output, cur);
+        cb(cur, "result_norm", -1);
 
+        cur = llm_build_lora_mm(lctx, ctx0, model.output, cur);
         cb(cur, "result_output", -1);
+
         ggml_build_forward_expand(gf, cur);
 
         return gf;