feat: 0.9.0 architecture integration & iOS/macOS native Llama.xcframework support

README.md

@@ -39,7 +39,7 @@ Then download the platform binary for your project:
 | Platform | Artifact | Where to put it |
 |---|---|---|
 | macOS (dev/test) | `libllama.dylib` + sibling `libggml*.dylib`, `libmtmd.dylib` | anywhere on disk; pass path to `LlamaEngine.spawn` |
-| iOS / macOS app | `llama.xcframework` (3 slices: `ios-arm64`, `ios-arm64-simulator`, `macos-arm64`) | drag into Xcode → "Embed & Sign" → call `LlamaEngine.spawnFromProcess` |
+| iOS / macOS app | `Llama.xcframework` (3 self-contained slices: `ios-arm64`, `ios-arm64_x86_64-simulator` [universal fat binary], `macos-arm64`) | Auto-linked via Flutter CocoaPods or drag into Xcode → "Embed & Sign" → call `LlamaEngine.spawnFromProcess` |
 | Android | `llama-cpp-dart.aar` (CPU + mtmd, arm64-v8a) **or** `llama-cpp-dart-hexagon.aar` (CPU + OpenCL + Hexagon NPU + mtmd, arm64-v8a, Snapdragon) | `android/app/libs/` and `implementation files('libs/llama-cpp-dart.aar')` in Gradle |
 
 Build artifacts yourself with:

ios/Llama.xcframework/Info.plist

@@ -0,0 +1,58 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+	<key>AvailableLibraries</key>
+	<array>
+		<dict>
+			<key>BinaryPath</key>
+			<string>Llama.framework/Llama</string>
+			<key>LibraryIdentifier</key>
+			<string>ios-arm64</string>
+			<key>LibraryPath</key>
+			<string>Llama.framework</string>
+			<key>SupportedArchitectures</key>
+			<array>
+				<string>arm64</string>
+			</array>
+			<key>SupportedPlatform</key>
+			<string>ios</string>
+		</dict>
+		<dict>
+			<key>BinaryPath</key>
+			<string>Llama.framework/Llama</string>
+			<key>LibraryIdentifier</key>
+			<string>ios-arm64_x86_64-simulator</string>
+			<key>LibraryPath</key>
+			<string>Llama.framework</string>
+			<key>SupportedArchitectures</key>
+			<array>
+				<string>arm64</string>
+				<string>x86_64</string>
+			</array>
+			<key>SupportedPlatform</key>
+			<string>ios</string>
+			<key>SupportedPlatformVariant</key>
+			<string>simulator</string>
+		</dict>
+		<dict>
+			<key>BinaryPath</key>
+			<string>Llama.framework/Versions/A/Llama</string>
+			<key>LibraryIdentifier</key>
+			<string>macos-arm64</string>
+			<key>LibraryPath</key>
+			<string>Llama.framework</string>
+			<key>SupportedArchitectures</key>
+			<array>
+				<string>arm64</string>
+			</array>
+			<key>SupportedPlatform</key>
+			<string>macos</string>
+		</dict>
+	</array>
+	<key>CFBundlePackageType</key>
+	<string>XFWK</string>
+	<key>XCFrameworkFormatVersion</key>
+	<string>1.0</string>
+</dict>
+</plist>

ios/Llama.xcframework/ios-arm64/Llama.framework/Headers/ggml-alloc.h

@@ -0,0 +1,86 @@
+#pragma once
+
+#include "ggml.h"
+
+#ifdef  __cplusplus
+extern "C" {
+#endif
+
+typedef struct ggml_backend_buffer_type * ggml_backend_buffer_type_t;
+typedef struct      ggml_backend_buffer * ggml_backend_buffer_t;
+typedef struct             ggml_backend * ggml_backend_t;
+
+// Tensor allocator
+struct ggml_tallocr {
+    ggml_backend_buffer_t buffer;
+    void * base;
+    size_t alignment;
+    size_t offset;
+};
+
+GGML_API struct ggml_tallocr ggml_tallocr_new(ggml_backend_buffer_t buffer);
+GGML_API enum ggml_status    ggml_tallocr_alloc(struct ggml_tallocr * talloc, struct ggml_tensor * tensor);
+
+// Graph allocator
+/*
+  Example usage:
+    ggml_gallocr_t galloc = ggml_gallocr_new(ggml_backend_cpu_buffer_type());
+
+    // optional: create a worst-case graph and reserve the buffers to avoid reallocations
+    ggml_gallocr_reserve(galloc, build_graph(max_batch));
+
+    // allocate the graph
+    struct ggml_cgraph * graph = build_graph(batch);
+    ggml_gallocr_alloc_graph(galloc, graph);
+
+    printf("compute buffer size: %zu bytes\n", ggml_gallocr_get_buffer_size(galloc, 0));
+
+    // evaluate the graph
+    ggml_backend_graph_compute(backend, graph);
+*/
+
+// special tensor flags for use with the graph allocator:
+//   ggml_set_input(): all input tensors are allocated at the beginning of the graph in non-overlapping addresses
+//   ggml_set_output(): output tensors are never freed and never overwritten
+
+typedef struct ggml_gallocr * ggml_gallocr_t;
+
+GGML_API ggml_gallocr_t ggml_gallocr_new(ggml_backend_buffer_type_t buft);
+GGML_API ggml_gallocr_t ggml_gallocr_new_n(ggml_backend_buffer_type_t * bufts, int n_bufs);
+GGML_API void           ggml_gallocr_free(ggml_gallocr_t galloc);
+
+// pre-allocate buffers from a measure graph - does not allocate or modify the graph
+// call with a worst-case graph to avoid buffer reallocations
+// not strictly required for single buffer usage: ggml_gallocr_alloc_graph will reallocate the buffers automatically if needed
+// returns false if the buffer allocation failed
+// ggml_gallocr_resrve_n_size writes the buffer sizes per galloc buffer that would be allocated by ggml_gallocr_reserve_n to sizes
+GGML_API bool ggml_gallocr_reserve(ggml_gallocr_t galloc, struct ggml_cgraph * graph);
+GGML_API void ggml_gallocr_reserve_n_size(
+    ggml_gallocr_t galloc,
+    struct ggml_cgraph * graph,
+    const int * node_buffer_ids,
+    const int * leaf_buffer_ids,
+    size_t * sizes);
+GGML_API bool ggml_gallocr_reserve_n(
+    ggml_gallocr_t galloc,
+    struct ggml_cgraph * graph,
+    const int * node_buffer_ids,
+    const int * leaf_buffer_ids);
+
+// automatic reallocation if the topology changes when using a single buffer
+// returns false if using multiple buffers and a re-allocation is needed (call ggml_gallocr_reserve_n first to set the node buffers)
+GGML_API bool ggml_gallocr_alloc_graph(ggml_gallocr_t galloc, struct ggml_cgraph * graph);
+
+GGML_API size_t ggml_gallocr_get_buffer_size(ggml_gallocr_t galloc, int buffer_id);
+
+// Utils
+// Create a buffer and allocate all the tensors in a ggml_context
+// ggml_backend_alloc_ctx_tensors_from_buft_size returns the size of the buffer that would be allocated by ggml_backend_alloc_ctx_tensors_from_buft
+// ggml_backend_alloc_ctx_tensors_from_buft returns NULL on failure or if all tensors in ctx are already allocated or zero-sized
+GGML_API size_t                       ggml_backend_alloc_ctx_tensors_from_buft_size(struct ggml_context * ctx, ggml_backend_buffer_type_t buft);
+GGML_API struct ggml_backend_buffer * ggml_backend_alloc_ctx_tensors_from_buft(struct ggml_context * ctx, ggml_backend_buffer_type_t buft);
+GGML_API struct ggml_backend_buffer * ggml_backend_alloc_ctx_tensors(struct ggml_context * ctx, ggml_backend_t backend);
+
+#ifdef  __cplusplus
+}
+#endif