Remove submodule and shift to Go server - 0.4.0 (#7157)

* Remove llama.cpp submodule and shift new build to top

* CI: install msys and clang gcc on win

Needed for deepseek to work properly on windows

llm/generate/generate_darwin.go

-package generate
-
-//go:generate bash ./gen_darwin.sh

llm/generate/generate_linux.go

-package generate
-
-//go:generate bash ./gen_linux.sh

llm/generate/generate_windows.go

-package generate
-
-//go:generate powershell -ExecutionPolicy Bypass -File ./gen_windows.ps1

llama.cpp @ 3f1ae2e3

-Subproject commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555

llm/patches/0000-cmakelist.patch

-From 7a3555098d4591c9b329c677654497ed8cee07ec Mon Sep 17 00:00:00 2001
-From: Michael Yang <mxyng@pm.me>
-Date: Fri, 23 Aug 2024 11:27:48 -0700
-Subject: [PATCH] patch cmakelist
-
----
- CMakeLists.txt | 2 ++
- 1 file changed, 2 insertions(+)
-
-diff --git a/CMakeLists.txt b/CMakeLists.txt
-index 415743c2..aaadd13e 100644
---- a/CMakeLists.txt
-+++ b/CMakeLists.txt
-@@ -210,3 +210,5 @@ if (LLAMA_BUILD_EXAMPLES)
-     add_subdirectory(examples)
-     add_subdirectory(pocs)
- endif()
-+
-+add_subdirectory(../ext_server ext_server) # ollama
--- 
-2.39.3 (Apple Git-146)
-

llm/patches/0002-clip-log.patch

-From 6fdf4268e13e56f0050fa6a29b029cbd54be49d2 Mon Sep 17 00:00:00 2001
-From: Gabe Goodhart <ghart@us.ibm.com>
-Date: Thu, 19 Sep 2024 16:58:03 -0600
-Subject: [PATCH] clip log
-
----
- examples/llava/clip.cpp | 1 +
- 1 file changed, 1 insertion(+)
-
-diff --git a/examples/llava/clip.cpp b/examples/llava/clip.cpp
-index 8aa7b075..b8941c74 100644
---- a/examples/llava/clip.cpp
-+++ b/examples/llava/clip.cpp
-@@ -3,6 +3,7 @@
- // I'll gradually clean and extend it
- // Note: Even when using identical normalized image inputs (see normalize_image_u8_to_f32()) we have a significant difference in resulting embeddings compared to pytorch
- #include "clip.h"
-+#include "common.h"
- #include "ggml.h"
- #include "ggml-alloc.h"
- #include "ggml-backend.h"
--- 
-2.39.3 (Apple Git-146)
-