llama : minor fixes for up llama load model speed (#11448)

* impl::load change map bpe_ranks to onordered map for reduce time of impl::load on 30%

* llama_model_loader::init_mapping - replace new llama_mmap to std::make_unique<llama_mmap> for clean code & reduce (/2) time of running init_mappings

* Update src/llama-vocab.cpp

---------

Co-authored-by: lexasub <[email protected]>
Co-authored-by: Diego Devesa <[email protected]>

Author: 3 people

src/llama-model-loader.cpp

@@ -819,7 +819,7 @@ void llama_model_loader::init_mappings(bool prefetch, llama_mlocks * mlock_mmaps
         for (const auto & file : files) {
             auto * reg = ggml_backend_dev_backend_reg(ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_CPU));
             auto * is_numa_fn = (decltype(ggml_is_numa) *) ggml_backend_reg_get_proc_address(reg, "ggml_backend_cpu_is_numa");
-            std::unique_ptr<llama_mmap> mapping(new llama_mmap(file.get(), prefetch ? -1 : 0, is_numa_fn()));
+            std::unique_ptr<llama_mmap> mapping = std::make_unique<llama_mmap>(file.get(), prefetch ? -1 : 0, is_numa_fn());
             mmaps_used.emplace_back(mapping->size(), 0);
             if (mlock_mmaps) {
                 std::unique_ptr<llama_mlock> mlock_mmap(new llama_mlock());

src/llama-vocab.cpp

@@ -1245,8 +1245,13 @@ struct llama_vocab::impl {
 
     std::vector<llama_token> cache_special_tokens;
     std::vector<std::string> cache_token_to_piece; // llama_token_to_piece(special = true);
-
-    std::map<std::pair<std::string, std::string>, int> bpe_ranks;
+    struct pair_hash {
+        size_t operator()(const std::pair<std::string, std::string> & p) const {
+            return std::hash<std::string>{}(p.first) ^  //create some hash for pair
+                   (std::hash<std::string>{}(p.second) << 1);
+        }
+    };
+    std::unordered_map<std::pair<std::string, std::string>, int, pair_hash> bpe_ranks;
 
     // set of all tokens that cause "end of generation"
     std::set<llama_token> special_eog_ids;