3 files changed, 67 insertions, 0 deletions
diff --git a/examples/quantize/CMakeLists.txt b/examples/quantize/CMakeLists.txt
new file mode 100644
index 0000000..fb27d45
--- /dev/null
+++ b/examples/quantize/CMakeLists.txt
@@ -0,0 +1,4 @@
+set(TARGET quantize)
+add_executable(${TARGET} quantize.cpp)
+target_link_libraries(${TARGET} PRIVATE llama ${CMAKE_THREAD_LIBS_INIT})
+target_compile_features(${TARGET} PRIVATE cxx_std_11)
diff --git a/examples/quantize/README.md b/examples/quantize/README.md
new file mode 100644
index 0000000..f349e91
--- /dev/null
+++ b/examples/quantize/README.md
@@ -0,0 +1,3 @@
+# quantize
+
+TODO
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp
new file mode 100644
index 0000000..f0230f5
--- /dev/null
+++ b/examples/quantize/quantize.cpp
@@ -0,0 +1,60 @@
+#include "ggml.h"
+#include "llama.h"
+
+#include <cstdio>
+#include <string>
+
+const int QK = 32;
+
+// usage:
+//  ./llama-quantize models/llama/ggml-model.bin models/llama/ggml-model-quant.bin type
+//
+int main(int argc, char ** argv) {
+    ggml_time_init();
+
+    if (argc != 4) {
+        fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type\n", argv[0]);
+        fprintf(stderr, "  type = 2 - q4_0\n");
+        fprintf(stderr, "  type = 3 - q4_1\n");
+        return 1;
+    }
+
+    // needed to initialize f16 tables
+    {
+        struct ggml_init_params params = { 0, NULL };
+        struct ggml_context * ctx = ggml_init(params);
+        ggml_free(ctx);
+    }
+
+    const std::string fname_inp = argv[1];
+    const std::string fname_out = argv[2];
+
+    const int itype = atoi(argv[3]);
+
+    const int64_t t_main_start_us = ggml_time_us();
+
+    int64_t t_quantize_us = 0;
+
+    // load the model
+    {
+        const int64_t t_start_us = ggml_time_us();
+
+        if (llama_model_quantize(fname_inp.c_str(), fname_out.c_str(), itype, QK)) {
+            fprintf(stderr, "%s: failed to quantize model from '%s'\n", __func__, fname_inp.c_str());
+            return 1;
+        }
+
+        t_quantize_us = ggml_time_us() - t_start_us;
+    }
+
+    // report timing
+    {
+        const int64_t t_main_end_us = ggml_time_us();
+
+        printf("\n");
+        printf("%s: quantize time = %8.2f ms\n", __func__, t_quantize_us/1000.0f);
+        printf("%s:    total time = %8.2f ms\n", __func__, (t_main_end_us - t_main_start_us)/1000.0f);
+    }
+
+    return 0;
+}