chore: bump llama.cpp

Signed-off-by: thxCode <thxcode0824@gmail.com>

Author: thxCode

llama-box/patches/llama.cpp/dynamic_link.patch

@@ -1,8 +1,8 @@
 diff --git a/ggml/src/ggml-cpu/ggml-cpu.cpp b/ggml/src/ggml-cpu/ggml-cpu.cpp
-index c9daa4c39..26f219c47 100644
+index e16cdc9d4..b8d1c41e5 100644
 --- a/ggml/src/ggml-cpu/ggml-cpu.cpp
 +++ b/ggml/src/ggml-cpu/ggml-cpu.cpp
-@@ -635,6 +635,18 @@ static void * ggml_backend_cpu_get_proc_address(ggml_backend_reg_t reg, const ch
+@@ -632,6 +632,18 @@ static void * ggml_backend_cpu_get_proc_address(ggml_backend_reg_t reg, const ch
      if (strcmp(name, "ggml_backend_cpu_is_numa") == 0) {
          return (void *)ggml_is_numa;
      }

llama-box/patches/llama.cpp/max_devices.patch

@@ -1,5 +1,5 @@
 diff --git a/ggml/src/ggml-backend.cpp b/ggml/src/ggml-backend.cpp
-index eaf41e5a6..a457fd4a1 100644
+index 1b9d29e91..8bdb5a0b7 100644
 --- a/ggml/src/ggml-backend.cpp
 +++ b/ggml/src/ggml-backend.cpp
 @@ -594,7 +594,7 @@ static bool ggml_is_view_op(enum ggml_op op) {

llama-box/patches/llama.cpp/template.patch

@@ -1,5 +1,5 @@
 diff --git a/src/llama-chat.cpp b/src/llama-chat.cpp
-index 1baf7350a..a3dafd45e 100644
+index 0a96a9a57..f98b82b11 100644
 --- a/src/llama-chat.cpp
 +++ b/src/llama-chat.cpp
 @@ -60,6 +60,9 @@ static const std::map<std::string, llm_chat_template> LLM_CHAT_TEMPLATES = {

llama-box/patches/llama.cpp/tool_calling.patch

@@ -222,7 +222,7 @@ index 545e957e5..25ce2de25 100644
      /// Both "model" and "custom_template" are optional, but at least one is required. "custom_template" has higher precedence than "model"
      /// NOTE: This function does not use a jinja parser. It only support a pre-defined list of template. See more: https://github.com/ggml-org/llama.cpp/wiki/Templates-supported-by-llama_chat_apply_template
 diff --git a/src/llama-chat.cpp b/src/llama-chat.cpp
-index 1baf7350a..5cc21afa9 100644
+index 0a96a9a57..ec0665e0d 100644
 --- a/src/llama-chat.cpp
 +++ b/src/llama-chat.cpp
 @@ -205,6 +205,606 @@ llm_chat_template llm_chat_detect_template(const std::string & tmpl) {