llama: Decouple patching script from submodule (#7139)

* Refine llama.cpp vendoring workflow tools

Switch from the sync.sh over to make based tooling

* Run new make sync and patch flow

llama/patches/0001-cuda.patch

@@ -0,0 +1,65 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: jmorganca <jmorganca@gmail.com>
+Date: Thu, 6 Jun 2024 23:55:47 -0700
+Subject: [PATCH] cuda
+
+---
+ ggml/include/ggml-cuda.h | 2 ++
+ ggml/src/ggml-backend.c  | 5 +++++
+ ggml/src/ggml-cuda.cu    | 6 ++++--
+ 3 files changed, 11 insertions(+), 2 deletions(-)
+
+diff --git a/ggml/include/ggml-cuda.h b/ggml/include/ggml-cuda.h
+index 71bb6dcf..08be0895 100644
+--- a/ggml/include/ggml-cuda.h
++++ b/ggml/include/ggml-cuda.h
+@@ -34,6 +34,8 @@ GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_cuda_split_buffer_typ
+ // pinned host buffer for use with the CPU backend for faster copies between CPU and GPU
+ GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_cuda_host_buffer_type(void);
+ 
++GGML_API GGML_CALL int ggml_backend_cuda_reg_devices();
++
+ GGML_API GGML_CALL int  ggml_backend_cuda_get_device_count(void);
+ GGML_API GGML_CALL void ggml_backend_cuda_get_device_description(int device, char * description, size_t description_size);
+ GGML_API GGML_CALL void ggml_backend_cuda_get_device_memory(int device, size_t * free, size_t * total);
+diff --git a/ggml/src/ggml-backend.c b/ggml/src/ggml-backend.c
+index ba280e06..d5c3fe49 100644
+--- a/ggml/src/ggml-backend.c
++++ b/ggml/src/ggml-backend.c
+@@ -83,7 +83,12 @@ void ggml_backend_buffer_free(ggml_backend_buffer_t buffer) {
+     if (buffer->iface.free_buffer != NULL) {
+         buffer->iface.free_buffer(buffer);
+     }
++
++// TODO: this needs to be freed in cuda and hipblas backends because
++// the cuda backend implementation compiled with msvc
++#if !defined(GGML_USE_CUDA) && !defined(GGML_USE_HIPBLAS)
+     free(buffer);
++#endif
+ }
+ 
+ size_t ggml_backend_buffer_get_size(ggml_backend_buffer_t buffer) {
+diff --git a/ggml/src/ggml-cuda.cu b/ggml/src/ggml-cuda.cu
+index 6efdab14..809d6ab1 100644
+--- a/ggml/src/ggml-cuda.cu
++++ b/ggml/src/ggml-cuda.cu
+@@ -469,6 +469,10 @@ GGML_CALL static bool ggml_backend_buffer_is_cuda(ggml_backend_buffer_t buffer)
+ GGML_CALL static void ggml_backend_cuda_buffer_free_buffer(ggml_backend_buffer_t buffer) {
+     ggml_backend_cuda_buffer_context * ctx = (ggml_backend_cuda_buffer_context *)buffer->context;
+     delete ctx;
++
++    // TODO: this needs to be freed in cuda and hipblas backends because
++    // the cuda backend implementation compiled with msvc
++    free(buffer);
+ }
+ 
+ GGML_CALL static void * ggml_backend_cuda_buffer_get_base(ggml_backend_buffer_t buffer) {
+@@ -3204,8 +3208,6 @@ GGML_CALL static ggml_backend_t ggml_backend_reg_cuda_init(const char * params,
+     GGML_UNUSED(params);
+ }
+ 
+-extern "C" GGML_CALL int ggml_backend_cuda_reg_devices();
+-
+ GGML_CALL int ggml_backend_cuda_reg_devices() {
+     int device_count = ggml_backend_cuda_get_device_count();
+     //int device_count = 1; // DEBUG: some tools require delaying CUDA initialization