Merge 7323304092 into 9a483999a6

Signed-off-by: kerthcet <kerthcet@gmail.com>

README.md

@@ -200,6 +200,7 @@ Instructions for adding support for new models: [HOWTO-add-model.md](docs/develo
 <details>
 <summary>Infrastructure</summary>
 
+- [llmaz](https://github.com/InftyAI/llmaz) - ☸️ Effortlessly serve state-of-the-art LLMs on Kubernetes, see [llama.cpp example](https://github.com/InftyAI/llmaz/tree/main/docs/examples/llamacpp) here.
 - [Paddler](https://github.com/distantmagic/paddler) - Stateful load balancer custom-tailored for llama.cpp
 - [GPUStack](https://github.com/gpustack/gpustack) - Manage GPU clusters for running LLMs
 - [llama_cpp_canister](https://github.com/onicai/llama_cpp_canister) - llama.cpp as a smart contract on the Internet Computer, using WebAssembly

common/common.cpp

@@ -1636,15 +1636,8 @@ std::string common_detokenize(const struct llama_vocab * vocab, const std::vecto
 //
 
 std::string common_get_builtin_chat_template(const struct llama_model * model) {
-    static const char * template_key = "tokenizer.chat_template";
-    // call with NULL buffer to get the total size of the string
-    int32_t res = llama_model_meta_val_str(model, template_key, NULL, 0);
-    if (res > 0) {
-        std::vector<char> model_template(res + 1, 0);
-        llama_model_meta_val_str(model, template_key, model_template.data(), model_template.size());
-        return std::string(model_template.data(), model_template.size() - 1);
-    }
-    return "";
+    const char * ptr_tmpl = llama_model_chat_template(model);
+    return ptr_tmpl == nullptr ? "" : ptr_tmpl;
 }
 
 bool common_chat_verify_template(const std::string & tmpl) {

src/llama-arch.cpp

@@ -178,7 +178,7 @@ static const std::map<llm_kv, const char *> LLM_KV_NAMES = {
     { LLM_KV_TOKENIZER_PRECOMPILED_CHARSMAP, "tokenizer.ggml.precompiled_charsmap"     },
     { LLM_KV_TOKENIZER_HF_JSON,              "tokenizer.huggingface.json"              },
     { LLM_KV_TOKENIZER_RWKV,                 "tokenizer.rwkv.world"                    },
-    { LLM_KV_TOKENIZER_CHAT_TEMPLATE,        "tokenizer.chat.template"                 },
+    { LLM_KV_TOKENIZER_CHAT_TEMPLATE,        "tokenizer.chat_template"                 },
     { LLM_KV_TOKENIZER_FIM_PRE_ID,           "tokenizer.ggml.fim_pre_token_id"         },
     { LLM_KV_TOKENIZER_FIM_SUF_ID,           "tokenizer.ggml.fim_suf_token_id"         },
     { LLM_KV_TOKENIZER_FIM_MID_ID,           "tokenizer.ggml.fim_mid_token_id"         },