Apply city96 lcpp.patch on tag b3962

Pre-applied patch for the ComfyUI-GGUF conversion toolchain
(https://github.com/Randy420Marsh/ComfyUI-GGUF), originally distributed
as tools/lcpp.patch in that repo. The patch:

* Doubles GGML_MAX_NAME (64 -> 128) so quantization can preserve longer
  diffusion-model tensor names.
* Adds gguf_set_tensor_ndim() to ggml.{h,c} so writer code can override
  the on-disk ndim metadata for tensors whose stored shape differs from
  the runtime ndim (used by Comfy diffusion archs where 5D tensors get
  reshaped to 4D for storage).
* Adjusts src/llama.cpp tensor-name handling to use the new
  GGML_MAX_NAME bound.

Source patch: tools/lcpp.patch in Randy420Marsh/ComfyUI-GGUF, sha-pinned
against this exact b3962 commit (c8c07d6). Re-applies cleanly with
'git apply --check' here.

Users of Randy420Marsh/ComfyUI-GGUF/tools should clone this branch
directly instead of cloning ggml-org/llama.cpp + checking out b3962
+ applying the patch by hand:

    git clone -b city96 https://github.com/Randy420Marsh/llama.cpp.git
    cd llama.cpp
    cmake -B build -DBUILD_SHARED_LIBS=ON
    cmake --build build --config Release -j

Then llama-quantize, libggml.so, libllama.so live in build/bin and
build/{src,ggml/src} as usual.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

Author: Randy420Marsh

ggml/include/ggml.h

@@ -223,7 +223,7 @@
 #define GGML_MAX_OP_PARAMS      64
 
 #ifndef GGML_MAX_NAME
-#   define GGML_MAX_NAME        64
+#   define GGML_MAX_NAME        128
 #endif
 
 #define GGML_DEFAULT_N_THREADS  4
@@ -2449,6 +2449,7 @@ extern "C" {
 
     // manage tensor info
     GGML_API void gguf_add_tensor(struct gguf_context * ctx, const struct ggml_tensor * tensor);
+    GGML_API void gguf_set_tensor_ndim(struct gguf_context * ctx, const char * name, int n_dim);
     GGML_API void gguf_set_tensor_type(struct gguf_context * ctx, const char * name, enum ggml_type type);
     GGML_API void gguf_set_tensor_data(struct gguf_context * ctx, const char * name, const void * data, size_t size);
 

ggml/src/ggml.c

@@ -22960,6 +22960,14 @@ void gguf_add_tensor(
     ctx->header.n_tensors++;
 }
 
+void gguf_set_tensor_ndim(struct gguf_context * ctx, const char * name, const int n_dim) {
+    const int idx = gguf_find_tensor(ctx, name);
+    if (idx < 0) {
+        GGML_ABORT("tensor not found");
+    }
+    ctx->infos[idx].n_dims = n_dim;
+}
+
 void gguf_set_tensor_type(struct gguf_context * ctx, const char * name, enum ggml_type type) {
     const int idx = gguf_find_tensor(ctx, name);
     if (idx < 0) {