local-llm-rn 1.0.0

package/cpp/mtmd/mtmd.h

@@ -0,0 +1,319 @@
+#ifndef MTMD_H
+#define MTMD_H
+
+#include "ggml.h"
+#include "llama.h"
+
+#include <stddef.h>
+#include <stdint.h>
+#include <stdbool.h>
+
+#ifdef __cplusplus
+#include <string>
+#include <vector>
+#include <cinttypes>
+#include <memory>
+#endif
+
+/**
+ * libmtmd: A library for multimodal support in llama.cpp.
+ *
+ * WARNING: This API is experimental and subject to many BREAKING CHANGES.
+ *          Issues related to API usage may receive lower priority support.
+ *
+ * For the usage, see an example in mtmd-cli.cpp
+ *
+ * For contributors:
+ * - Make sure the C API is aligned with the libllama C API (as in llama.h)
+ * - Do not include model name (e.g., qwen, gemma) in the API, use generic terms instead
+ * - Keep the API minimal, do not expose internal details unless necessary
+ *
+ * IMPORTANT: The mtmd module does NOT accept pull requests that are fully or predominantly AI-generated.
+ * We encourage human contributors to ensure the quality and reliability of the codebase.
+ */
+
+#ifdef LLAMA_SHARED
+#    if defined(_WIN32) && !defined(__MINGW32__)
+#        ifdef LLAMA_BUILD
+#            define MTMD_API __declspec(dllexport)
+#        else
+#            define MTMD_API __declspec(dllimport)
+#        endif
+#    else
+#        define MTMD_API __attribute__ ((visibility ("default")))
+#    endif
+#else
+#    define MTMD_API
+#endif
+
+// deprecated marker, use mtmd_default_marker() instead
+#define MTMD_DEFAULT_IMAGE_MARKER "<__image__>"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+enum mtmd_input_chunk_type {
+    MTMD_INPUT_CHUNK_TYPE_TEXT,
+    MTMD_INPUT_CHUNK_TYPE_IMAGE,
+    MTMD_INPUT_CHUNK_TYPE_AUDIO,
+};
+
+// opaque types
+struct mtmd_context;
+struct mtmd_bitmap;
+struct mtmd_image_tokens;
+struct mtmd_input_chunk;
+struct mtmd_input_chunks;
+
+struct mtmd_input_text {
+    const char * text;
+    bool add_special;
+    bool parse_special;
+};
+
+//
+// C API
+//
+
+typedef struct mtmd_context      mtmd_context;
+typedef struct mtmd_bitmap       mtmd_bitmap;
+typedef struct mtmd_image_tokens mtmd_image_tokens;
+typedef struct mtmd_input_chunk  mtmd_input_chunk;
+typedef struct mtmd_input_chunks mtmd_input_chunks;
+typedef struct mtmd_input_text   mtmd_input_text;
+
+struct mtmd_context_params {
+    bool use_gpu;
+    bool print_timings;
+    int n_threads;
+    const char * image_marker; // deprecated, use media_marker instead
+    const char * media_marker;
+    enum llama_flash_attn_type flash_attn_type;
+    bool warmup; // whether to run a warmup encode pass after initialization
+
+    // limit number of image tokens, only for vision models with dynamic resolution
+    int image_min_tokens; // minimum number of tokens for image input (default: read from metadata)
+    int image_max_tokens; // maximum number of tokens for image input (default: read from metadata)
+
+    // callback function passed over to mtmd proper
+    ggml_backend_sched_eval_callback cb_eval;
+    void * cb_eval_user_data;
+};
+
+MTMD_API const char * mtmd_default_marker(void);
+
+MTMD_API struct mtmd_context_params mtmd_context_params_default(void);
+
+// initialize the mtmd context
+// return nullptr on failure
+MTMD_API mtmd_context * mtmd_init_from_file(const char * mmproj_fname,
+                                            const struct llama_model * text_model,
+                                            const struct mtmd_context_params ctx_params);
+
+MTMD_API void mtmd_free(mtmd_context * ctx);
+
+// whether we need to set non-causal mask before llama_decode
+MTMD_API bool mtmd_decode_use_non_causal(mtmd_context * ctx);
+
+// whether the current model use M-RoPE for llama_decode
+MTMD_API bool mtmd_decode_use_mrope(mtmd_context * ctx);
+
+// whether the current model supports vision input
+MTMD_API bool mtmd_support_vision(mtmd_context * ctx);
+
+// whether the current model supports audio input
+MTMD_API bool mtmd_support_audio(mtmd_context * ctx);
+
+// get audio bitrate in Hz, for example 16000 for Whisper
+// return -1 if audio is not supported
+MTMD_API int mtmd_get_audio_bitrate(mtmd_context * ctx);
+
+// mtmd_bitmap
+//
+// if bitmap is image:
+//     length of data must be nx * ny * 3
+//     the data is in RGBRGBRGB... format
+// if bitmap is audio:
+//     length of data must be n_samples * sizeof(float)
+//     the data is in float format (PCM F32)
+MTMD_API mtmd_bitmap *         mtmd_bitmap_init           (uint32_t nx, uint32_t ny, const unsigned char * data);
+MTMD_API mtmd_bitmap *         mtmd_bitmap_init_from_audio(size_t n_samples,         const float         * data);
+MTMD_API uint32_t              mtmd_bitmap_get_nx     (const mtmd_bitmap * bitmap);
+MTMD_API uint32_t              mtmd_bitmap_get_ny     (const mtmd_bitmap * bitmap);
+MTMD_API const unsigned char * mtmd_bitmap_get_data   (const mtmd_bitmap * bitmap);
+MTMD_API size_t                mtmd_bitmap_get_n_bytes(const mtmd_bitmap * bitmap);
+MTMD_API bool                  mtmd_bitmap_is_audio   (const mtmd_bitmap * bitmap);
+MTMD_API void                  mtmd_bitmap_free       (mtmd_bitmap * bitmap);
+// bitmap ID is optional, but useful for KV cache tracking
+// these getters/setters are dedicated functions, so you can for example calculate the hash of the image based on mtmd_bitmap_get_data()
+MTMD_API const char * mtmd_bitmap_get_id(const mtmd_bitmap * bitmap);
+MTMD_API void         mtmd_bitmap_set_id(mtmd_bitmap * bitmap, const char * id);
+
+
+// mtmd_input_chunks
+//
+// this is simply a list of mtmd_input_chunk
+// the elements can only be populated via mtmd_tokenize()
+MTMD_API mtmd_input_chunks *      mtmd_input_chunks_init(void);
+MTMD_API size_t                   mtmd_input_chunks_size(const mtmd_input_chunks * chunks);
+MTMD_API const mtmd_input_chunk * mtmd_input_chunks_get (const mtmd_input_chunks * chunks, size_t idx);
+MTMD_API void                     mtmd_input_chunks_free(mtmd_input_chunks * chunks);
+
+// mtmd_input_chunk
+//
+// the instance will be constructed via mtmd_tokenize()
+// it will be freed along with mtmd_input_chunks
+MTMD_API enum mtmd_input_chunk_type mtmd_input_chunk_get_type        (const mtmd_input_chunk * chunk);
+MTMD_API const llama_token *        mtmd_input_chunk_get_tokens_text (const mtmd_input_chunk * chunk, size_t * n_tokens_output);
+MTMD_API const mtmd_image_tokens *  mtmd_input_chunk_get_tokens_image(const mtmd_input_chunk * chunk);
+MTMD_API size_t                     mtmd_input_chunk_get_n_tokens    (const mtmd_input_chunk * chunk);
+// returns nullptr for ID on text chunk
+MTMD_API const char *               mtmd_input_chunk_get_id          (const mtmd_input_chunk * chunk);
+// number of temporal positions (equals to max(t,h,w) for M-RoPE; equals to n_tokens otherwise)
+MTMD_API llama_pos                  mtmd_input_chunk_get_n_pos       (const mtmd_input_chunk * chunk);
+
+// in case you want to use custom logic to handle the chunk (i.e. KV cache management)
+// you can move the chunk ownership to your own code by copying it
+// remember to free the chunk when you are done with it
+MTMD_API mtmd_input_chunk * mtmd_input_chunk_copy(const mtmd_input_chunk * chunk);
+MTMD_API void               mtmd_input_chunk_free(mtmd_input_chunk * chunk);
+
+
+// mtmd_image_tokens
+//
+// the instance will be constructed via mtmd_tokenize()
+// it will be freed along with mtmd_input_chunk
+MTMD_API size_t       mtmd_image_tokens_get_n_tokens(const mtmd_image_tokens * image_tokens); // TODO: deprecate
+MTMD_API size_t       mtmd_image_tokens_get_nx      (const mtmd_image_tokens * image_tokens);
+MTMD_API size_t       mtmd_image_tokens_get_ny      (const mtmd_image_tokens * image_tokens);
+MTMD_API const char * mtmd_image_tokens_get_id      (const mtmd_image_tokens * image_tokens); // TODO: deprecate
+// number of temporal positions (equals to max(t,h,w) for M-RoPE; equals to n_tokens otherwise)
+MTMD_API llama_pos    mtmd_image_tokens_get_n_pos   (const mtmd_image_tokens * image_tokens); // TODO: deprecate
+
+// tokenize an input text prompt and a list of bitmaps (images/audio)
+// the prompt must have the input image marker (default: "<__media__>") in it
+// the default marker is defined by mtmd_default_marker()
+// the marker will be replaced with the image/audio chunk
+// for example:
+//   "here is an image: <__media__>\ndescribe it in detail."
+//   this will gives 3 chunks:
+//   1. "here is an image: <start_of_image>"
+//   2. (image/audio tokens)
+//   3. "<end_of_image>\ndescribe it in detail."
+// number of bitmaps must be equal to the number of markers in the prompt
+// this function is thread-safe (shared ctx)
+// return values:
+//   0 on success
+//   1 on number of bitmaps not matching the number of markers
+//   2 on image preprocessing error
+MTMD_API int32_t mtmd_tokenize(mtmd_context * ctx,
+                               mtmd_input_chunks * output,
+                               const mtmd_input_text * text,
+                               const mtmd_bitmap ** bitmaps,
+                               size_t n_bitmaps);
+
+// returns 0 on success
+// TODO: deprecate
+MTMD_API int32_t mtmd_encode(mtmd_context * ctx,
+                             const mtmd_image_tokens * image_tokens);
+
+// returns 0 on success
+MTMD_API int32_t mtmd_encode_chunk(mtmd_context * ctx,
+                                   const mtmd_input_chunk * chunk);
+
+// get output embeddings from the last encode pass
+// the reading size (in bytes) is equal to:
+// llama_model_n_embd_inp(model) * mtmd_input_chunk_get_n_tokens(chunk) * sizeof(float)
+MTMD_API float * mtmd_get_output_embd(mtmd_context * ctx);
+
+// Set callback for all future logging events.
+// If this is not called, or NULL is supplied, everything is output on stderr.
+MTMD_API void mtmd_log_set(ggml_log_callback log_callback, void * user_data);
+
+/////////////////////////////////////////
+
+// test function, to be used in test-mtmd-c-api.c
+MTMD_API mtmd_input_chunks * mtmd_test_create_input_chunks(void);
+
+#ifdef __cplusplus
+} // extern "C"
+#endif
+
+//
+// C++ wrappers
+//
+
+#ifdef __cplusplus
+
+namespace mtmd {
+
+struct mtmd_context_deleter {
+    void operator()(mtmd_context * val) { mtmd_free(val); }
+};
+using context_ptr = std::unique_ptr<mtmd_context, mtmd_context_deleter>;
+
+struct mtmd_bitmap_deleter {
+    void operator()(mtmd_bitmap * val) { mtmd_bitmap_free(val); }
+};
+using bitmap_ptr = std::unique_ptr<mtmd_bitmap, mtmd_bitmap_deleter>;
+
+struct mtmd_input_chunks_deleter {
+    void operator()(mtmd_input_chunks * val) { mtmd_input_chunks_free(val); }
+};
+using input_chunks_ptr = std::unique_ptr<mtmd_input_chunks, mtmd_input_chunks_deleter>;
+
+struct mtmd_input_chunk_deleter {
+    void operator()(mtmd_input_chunk * val) { mtmd_input_chunk_free(val); }
+};
+using input_chunk_ptr = std::unique_ptr<mtmd_input_chunk, mtmd_input_chunk_deleter>;
+
+struct bitmap {
+    bitmap_ptr ptr;
+    bitmap() : ptr(nullptr) {}
+    bitmap(mtmd_bitmap * bitmap) : ptr(bitmap) {}
+    bitmap(bitmap && other) noexcept : ptr(std::move(other.ptr)) {}
+    bitmap(uint32_t nx, uint32_t ny, const unsigned char * data) {
+        ptr.reset(mtmd_bitmap_init(nx, ny, data));
+    }
+    ~bitmap() = default;
+    uint32_t nx() const { return mtmd_bitmap_get_nx(ptr.get()); }
+    uint32_t ny() const { return mtmd_bitmap_get_ny(ptr.get()); }
+    const unsigned char * data() const { return mtmd_bitmap_get_data(ptr.get()); }
+    size_t n_bytes() const { return mtmd_bitmap_get_n_bytes(ptr.get()); }
+    std::string id() const { return mtmd_bitmap_get_id(ptr.get()); }
+    void set_id(const char * id) const { mtmd_bitmap_set_id(ptr.get(), id); }
+};
+
+struct bitmaps {
+    std::vector<bitmap> entries;
+    ~bitmaps() = default;
+    // return list of pointers to mtmd_bitmap
+    // example:
+    //   auto bitmaps_c_ptr = bitmaps.c_ptr();
+    //   int32_t res = mtmd_tokenize(... bitmaps_c_ptr.data(), bitmaps_c_ptr.size());
+    std::vector<const mtmd_bitmap *> c_ptr() {
+        std::vector<const mtmd_bitmap *> res(entries.size());
+        for (size_t i = 0; i < entries.size(); i++) {
+            res[i] = entries[i].ptr.get();
+        }
+        return res;
+    }
+};
+
+struct input_chunks {
+    input_chunks_ptr ptr;
+    input_chunks() = default;
+    input_chunks(mtmd_input_chunks * chunks) : ptr(chunks) {}
+    ~input_chunks() = default;
+    size_t size() const { return mtmd_input_chunks_size(ptr.get()); }
+    const mtmd_input_chunk * operator[](size_t idx) const {
+        return mtmd_input_chunks_get(ptr.get(), idx);
+    }
+};
+
+} // namespace mtmd
+
+#endif
+
+#endif

package/cpp/mtmd/requirements.txt

@@ -0,0 +1,5 @@
+-r ../../requirements/requirements-convert_legacy_llama.txt
+--extra-index-url https://download.pytorch.org/whl/cpu
+pillow~=11.3.0
+torch~=2.6.0
+torchvision~=0.21.0

package/cpp/mtmd/tests.sh

@@ -0,0 +1,192 @@
+#!/usr/bin/env bash
+
+# make sure we are in the right directory
+SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+cd $SCRIPT_DIR
+
+#export LLAMA_CACHE="$SCRIPT_DIR/tmp"
+
+set -eux
+
+mkdir -p $SCRIPT_DIR/output
+
+PROJ_ROOT="$SCRIPT_DIR/../.."
+cd $PROJ_ROOT
+
+# Check if the first argument is "big", then run test with big models
+# This is useful if we're running the script on a larger machine, so we can test the big models
+RUN_BIG_TESTS=false
+if [ "${1:-}" = "big" ]; then
+    RUN_BIG_TESTS=true
+    echo "Include BIG models..."
+fi
+
+RUN_HUGE_TESTS=false
+if [ "${1:-}" = "huge" ]; then
+    RUN_HUGE_TESTS=true
+    RUN_BIG_TESTS=true
+    echo "Include BIG and HUGE models..."
+fi
+
+# Check if the second argument is "flash", then enable flash attention
+# This is useful to test if flash attention off works correctly
+FLASH_ATTN="on"
+if [ "${2:-}" = "flash_off" ] || [ "${1:-}" = "flash_off" ]; then
+    FLASH_ATTN="off"
+    echo "Flash attention disabled..."
+fi
+
+###############
+
+arr_prefix=()
+arr_hf=()
+arr_extra_args=()
+arr_file=()
+
+add_test_vision() {
+    local hf=$1
+    shift
+    local extra_args=""
+    if [ $# -gt 0 ]; then
+        extra_args=$(printf " %q" "$@")
+    fi
+    arr_prefix+=("[vision]")
+    arr_hf+=("$hf")
+    arr_extra_args+=("$extra_args")
+    arr_file+=("test-1.jpeg")
+}
+
+add_test_audio() {
+    local hf=$1
+    shift
+    local extra_args=""
+    if [ $# -gt 0 ]; then
+        extra_args=$(printf " %q" "$@")
+    fi
+    arr_prefix+=("[audio] ")
+    arr_hf+=("$hf")
+    arr_extra_args+=("$extra_args")
+    arr_file+=("test-2.mp3")
+}
+
+add_test_vision "ggml-org/SmolVLM-500M-Instruct-GGUF:Q8_0"
+add_test_vision "ggml-org/SmolVLM2-2.2B-Instruct-GGUF:Q4_K_M"
+add_test_vision "ggml-org/SmolVLM2-500M-Video-Instruct-GGUF:Q8_0"
+add_test_vision "ggml-org/gemma-3-4b-it-GGUF:Q4_K_M"
+add_test_vision "THUDM/glm-edge-v-5b-gguf:Q4_K_M" -p "name of the newspaper?<__media__>"
+add_test_vision "second-state/Llava-v1.5-7B-GGUF:Q2_K" --chat-template vicuna
+add_test_vision "cjpais/llava-1.6-mistral-7b-gguf:Q3_K_M" --chat-template vicuna
+add_test_vision "ibm-research/granite-vision-3.2-2b-GGUF:Q4_K_M"
+add_test_vision "second-state/MiniCPM-Llama3-V-2_5-GGUF:Q2_K"  # model from openbmb is corrupted
+add_test_vision "openbmb/MiniCPM-V-2_6-gguf:Q2_K"
+add_test_vision "openbmb/MiniCPM-o-2_6-gguf:Q4_0"
+add_test_vision "bartowski/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M"
+add_test_vision "ggml-org/Qwen2.5-VL-3B-Instruct-GGUF:Q4_K_M"
+add_test_vision "ggml-org/InternVL2_5-1B-GGUF:Q8_0"
+add_test_vision "ggml-org/InternVL3-1B-Instruct-GGUF:Q8_0"
+add_test_vision "ggml-org/Qwen2.5-Omni-3B-GGUF:Q4_K_M"
+add_test_vision "ggml-org/LFM2-VL-450M-GGUF:Q8_0"
+add_test_vision "ggml-org/granite-docling-258M-GGUF:Q8_0"
+add_test_vision "ggml-org/LightOnOCR-1B-1025-GGUF:Q8_0"
+
+add_test_audio  "ggml-org/ultravox-v0_5-llama-3_2-1b-GGUF:Q8_0"
+add_test_audio  "ggml-org/Qwen2.5-Omni-3B-GGUF:Q4_K_M"
+add_test_audio  "ggml-org/Voxtral-Mini-3B-2507-GGUF:Q4_K_M"
+add_test_audio  "ggml-org/LFM2-Audio-1.5B-GGUF:Q8_0"
+
+# to test the big models, run: ./tests.sh big
+if [ "$RUN_BIG_TESTS" = true ]; then
+    add_test_vision "ggml-org/pixtral-12b-GGUF:Q4_K_M"
+    add_test_vision "ggml-org/Mistral-Small-3.1-24B-Instruct-2503-GGUF" --chat-template mistral-v7
+    add_test_vision "ggml-org/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M"
+    add_test_vision "ggml-org/Qwen2-VL-7B-Instruct-GGUF:Q4_K_M"
+    add_test_vision "ggml-org/Qwen2.5-VL-3B-Instruct-GGUF:Q4_K_M"
+    add_test_vision "ggml-org/Qwen2.5-VL-7B-Instruct-GGUF:Q4_K_M"
+    add_test_vision "ggml-org/Qwen3-VL-2B-Instruct-GGUF:Q8_0"
+    add_test_vision "ggml-org/InternVL3-8B-Instruct-GGUF:Q4_K_M"
+    add_test_vision "ggml-org/InternVL3-14B-Instruct-GGUF:Q4_K_M"
+    add_test_vision "ggml-org/Qwen2.5-Omni-7B-GGUF:Q4_K_M"
+    # add_test_vision "ggml-org/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M" # does not work on my mac M3 Ultra
+    # add_test_vision "ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF:Q4_K_M" # not always working
+
+    add_test_audio  "ggml-org/ultravox-v0_5-llama-3_1-8b-GGUF:Q4_K_M"
+    add_test_audio  "ggml-org/Qwen2.5-Omni-7B-GGUF:Q4_K_M"
+fi
+
+# to test the huge models, run: ./tests.sh huge
+# this will run both the big and huge models
+# huge models are > 32B parameters
+if [ "$RUN_HUGE_TESTS" = true ]; then
+    add_test_vision "ggml-org/Qwen2.5-VL-72B-Instruct-GGUF:Q4_K_M"
+    add_test_vision "ggml-org/Llama-4-Scout-17B-16E-Instruct-GGUF:IQ1_S"
+fi
+
+# these models always give the wrong answer, not sure why
+# add_test_vision "ggml-org/SmolVLM-Instruct-GGUF:Q4_K_M"
+# add_test_vision "ggml-org/SmolVLM-256M-Instruct-GGUF:Q8_0"
+# add_test_vision "ggml-org/SmolVLM2-256M-Video-Instruct-GGUF:Q8_0"
+
+# this model has broken chat template, not usable
+# add_test_vision "cmp-nct/Yi-VL-6B-GGUF:Q5_K"
+# add_test_vision "guinmoon/MobileVLM-3B-GGUF:Q4_K_M" "deepseek"
+
+###############
+
+cmake --build build -j --target llama-mtmd-cli
+
+arr_res=()
+
+for i in "${!arr_hf[@]}"; do
+    bin="llama-mtmd-cli"
+    prefix="${arr_prefix[$i]}"
+    hf="${arr_hf[$i]}"
+    extra_args="${arr_extra_args[$i]}"
+    inp_file="${arr_file[$i]}"
+
+    echo "Running test with binary: $bin and HF model: $hf"
+    echo ""
+    echo ""
+
+    cmd="$(printf %q "$PROJ_ROOT/build/bin/$bin") \
+        -hf $(printf %q "$hf") \
+        --image $(printf %q "$SCRIPT_DIR/$inp_file") \
+        --temp 0 -n 128 \
+        --flash-attn $(printf %q "$FLASH_ATTN") \
+        ${extra_args}"
+
+    # if extra_args does not contain -p, we add a default prompt
+    if ! [[ "$extra_args" =~ "-p" ]]; then
+        cmd+=" -p \"what is the publisher name of the newspaper?\""
+    fi
+
+    output=$(eval "$cmd" 2>&1 | tee /dev/tty)
+
+    echo "$output" > $SCRIPT_DIR/output/$bin-$(echo "$hf" | tr '/' '-').log
+
+    # either contains "new york" or both "men" and "walk"
+    if echo "$output" | grep -iq "new york" \
+            || (echo "$output" | grep -iq "men" && echo "$output" | grep -iq "walk")
+    then
+        result="$prefix \033[32mOK\033[0m:   $hf"
+    else
+        result="$prefix \033[31mFAIL\033[0m: $hf"
+    fi
+    echo -e "$result"
+    arr_res+=("$result")
+
+    echo ""
+    echo ""
+    echo ""
+    echo "#################################################"
+    echo "#################################################"
+    echo ""
+    echo ""
+done
+
+set +x
+
+for i in "${!arr_res[@]}"; do
+    echo -e "${arr_res[$i]}"
+done
+echo ""
+echo "Output logs are saved in $SCRIPT_DIR/output"

package/cpp/src/CMakeLists.txt

@@ -0,0 +1,169 @@
+llama_add_compile_flags()
+
+#
+# libraries
+#
+
+# llama
+
+add_library(llama
+            ../include/llama.h
+            llama.cpp
+            llama-adapter.cpp
+            llama-arch.cpp
+            llama-batch.cpp
+            llama-chat.cpp
+            llama-context.cpp
+            llama-cparams.cpp
+            llama-grammar.cpp
+            llama-graph.cpp
+            llama-hparams.cpp
+            llama-impl.cpp
+            llama-io.cpp
+            llama-kv-cache.cpp
+            llama-kv-cache-iswa.cpp
+            llama-memory.cpp
+            llama-memory-hybrid.cpp
+            llama-memory-hybrid-iswa.cpp
+            llama-memory-recurrent.cpp
+            llama-mmap.cpp
+            llama-model-loader.cpp
+            llama-model-saver.cpp
+            llama-model.cpp
+            llama-quant.cpp
+            llama-sampler.cpp
+            llama-vocab.cpp
+            unicode-data.cpp
+            unicode.cpp
+            unicode.h
+            models/afmoe.cpp
+            models/apertus.cpp
+            models/arcee.cpp
+            models/arctic.cpp
+            models/arwkv7.cpp
+            models/baichuan.cpp
+            models/bailingmoe.cpp
+            models/bailingmoe2.cpp
+            models/bert.cpp
+            models/bitnet.cpp
+            models/bloom.cpp
+            models/chameleon.cpp
+            models/chatglm.cpp
+            models/codeshell.cpp
+            models/cogvlm.cpp
+            models/cohere2-iswa.cpp
+            models/command-r.cpp
+            models/dbrx.cpp
+            models/deci.cpp
+            models/deepseek.cpp
+            models/deepseek2.cpp
+            models/delta-net-base.cpp
+            models/dots1.cpp
+            models/dream.cpp
+            models/ernie4-5-moe.cpp
+            models/ernie4-5.cpp
+            models/eurobert.cpp
+            models/exaone-moe.cpp
+            models/exaone.cpp
+            models/exaone4.cpp
+            models/falcon-h1.cpp
+            models/falcon.cpp
+            models/gemma-embedding.cpp
+            models/gemma.cpp
+            models/gemma2-iswa.cpp
+            models/gemma3.cpp
+            models/gemma3n-iswa.cpp
+            models/glm4-moe.cpp
+            models/glm4.cpp
+            models/gpt2.cpp
+            models/gptneox.cpp
+            models/granite-hybrid.cpp
+            models/granite.cpp
+            models/grok.cpp
+            models/grovemoe.cpp
+            models/hunyuan-dense.cpp
+            models/hunyuan-moe.cpp
+            models/internlm2.cpp
+            models/jais.cpp
+            models/jais2.cpp
+            models/jamba.cpp
+            models/kimi-linear.cpp
+            models/lfm2.cpp
+            models/llada-moe.cpp
+            models/llada.cpp
+            models/llama-iswa.cpp
+            models/llama.cpp
+            models/maincoder.cpp
+            models/mamba-base.cpp
+            models/mamba.cpp
+            models/mimo2-iswa.cpp
+            models/minicpm3.cpp
+            models/minimax-m2.cpp
+            models/mistral3.cpp
+            models/modern-bert.cpp
+            models/mpt.cpp
+            models/nemotron-h.cpp
+            models/nemotron.cpp
+            models/neo-bert.cpp
+            models/olmo.cpp
+            models/olmo2.cpp
+            models/olmoe.cpp
+            models/openai-moe-iswa.cpp
+            models/openelm.cpp
+            models/orion.cpp
+            models/paddleocr.cpp
+            models/pangu-embedded.cpp
+            models/phi2.cpp
+            models/phi3.cpp
+            models/plamo.cpp
+            models/plamo2.cpp
+            models/plamo3.cpp
+            models/plm.cpp
+            models/qwen.cpp
+            models/qwen2.cpp
+            models/qwen2moe.cpp
+            models/qwen2vl.cpp
+            models/qwen3.cpp
+            models/qwen35.cpp
+            models/qwen35moe.cpp
+            models/qwen3moe.cpp
+            models/qwen3next.cpp
+            models/qwen3vl-moe.cpp
+            models/qwen3vl.cpp
+            models/refact.cpp
+            models/rnd1.cpp
+            models/rwkv6-base.cpp
+            models/rwkv6.cpp
+            models/rwkv6qwen2.cpp
+            models/rwkv7-base.cpp
+            models/rwkv7.cpp
+            models/seed-oss.cpp
+            models/smallthinker.cpp
+            models/smollm3.cpp
+            models/stablelm.cpp
+            models/starcoder.cpp
+            models/starcoder2.cpp
+            models/step35-iswa.cpp
+            models/t5-dec.cpp
+            models/t5-enc.cpp
+            models/wavtokenizer-dec.cpp
+            models/xverse.cpp
+            )
+
+set_target_properties(llama PROPERTIES
+    VERSION ${LLAMA_INSTALL_VERSION}
+    SOVERSION 0
+    MACHO_CURRENT_VERSION 0 # keep macOS linker from seeing oversized version number
+)
+
+target_include_directories(llama PRIVATE .)
+target_include_directories(llama PUBLIC ../include)
+target_compile_features   (llama PRIVATE cxx_std_17) # don't bump
+
+target_link_libraries(llama PUBLIC ggml)
+
+if (BUILD_SHARED_LIBS)
+    set_target_properties(llama PROPERTIES POSITION_INDEPENDENT_CODE ON)
+    target_compile_definitions(llama PRIVATE LLAMA_BUILD)
+    target_compile_definitions(llama PUBLIC  LLAMA_SHARED)
+endif()