revert: restore public graph helper usage

docs/build.md

@@ -33,9 +33,8 @@ cmake --build build-upstream --config Release
 ```
 
 Both patched and upstream builds use the selected library and matching private
-headers for application graph helpers and backend integration. The generic
-operator registration API remains in `ggml-ext.h`. Backend options such as
-`-DSD_CUDA=ON` apply to the selected tree as usual.
+headers for backend integration. Backend options such as `-DSD_CUDA=ON` apply
+to the selected tree as usual.
 
 `SD_USE_UPSTREAM_GGML` defaults to `OFF`, which enables the patched GGML
 extensions. Set it to `ON` when using upstream GGML; it selects the compatibility
@@ -53,8 +52,8 @@ quantization types remain available, subject to backend operator support.
 
 `SD_USE_SYSTEM_GGML=ON` instead links an installed GGML CMake package, located
 with `ggml_DIR` or `CMAKE_PREFIX_PATH`. An installed patched package must include
-the extension API. Set `SD_GGML_SOURCE_DIR` to its matching source tree for
-private graph and backend headers, including CUDA/HIP/MUSA vendor headers.
+the extension and graph APIs. Set `SD_GGML_SOURCE_DIR` to its matching source
+tree for private backend headers, including CUDA/HIP/MUSA vendor headers.
 The installed library must use the same ABI settings as sd.cpp,
 including `GGML_MAX_NAME`. For an upstream package, also set
 `SD_USE_UPSTREAM_GGML=ON` and point `SD_GGML_SOURCE_DIR` to its matching source

docs/ggml_extensions.md

@@ -448,18 +448,22 @@ kernel compiled for SM80 or newer. CPU, HIP, MUSA, and Vulkan do not advertise
 support. ggml no longer contains a Sol-Attn opcode, constructor, allocation rule,
 or backend kernel.
 
-## Internal graph access
+## Public graph access
 
-`src/core/ggml_compat.cpp` uses `ggml-impl.h` for leaf enumeration, graph copying,
-use-count preservation and range execution. Patched and upstream builds share
-this implementation; ggml does not expose a separate public graph API for these
-application helpers. Mapped copies retain node order and consumer counts,
-including consumers outside a graph view. Invalid mappings leave the destination
-unchanged. Workspace measurement, graph cuts and evaluation callbacks use these
-helpers.
+`ggml-graph.h` exposes leaf enumeration, append-only leaf construction, recorded
+use counts, mapped inference-graph copying, use-count copying for segments, and
+backend execution of a node range. Mapped copies retain node order and consumer
+counts from the original graph, including consumers outside a graph view. The
+caller owns tensor copies and remaps their storage and edges; invalid mappings
+leave the destination graph unchanged. Range execution uses already allocated
+tensors and retains the original graph's consumer counts.
 
-The compatibility layer also retains the workaround for old Metal backends
-wrapping failed host mappings. The patched Metal backend returns null directly.
+Workspace measurement, graph cuts, and evaluation callbacks use these APIs.
+Backend extensions require matching private headers. Compatibility with an
+upstream ggml lacking this header is isolated in `src/core/ggml_compat.cpp`; that
+optional build still requires matching upstream private headers. The compatibility
+layer also retains the workaround for old Metal backends wrapping failed host
+mappings. The patched Metal backend returns null directly when mapping fails.
 
 Vulkan command recording services are declared in the private
 `ggml/src/ggml-ext-vulkan.h`. Pipeline ownership, submission and synchronization