Use const; add basic test

ggml.c

@@ -10720,7 +10720,7 @@ enum ggml_opt_result ggml_opt(
 
 ////////////////////////////////////////////////////////////////////////////////
 
-size_t ggml_quantize_q4_0(float * src, void * dst, int n, int k, int qk, int64_t * hist) {
+size_t ggml_quantize_q4_0(const float * src, void * dst, int n, int k, int qk, int64_t * hist) {
     const int nb = k / qk;
     const size_t bs = (sizeof(float) + sizeof(uint8_t)*qk/2);
     const size_t row_size = nb*bs;
@@ -10750,7 +10750,7 @@ size_t ggml_quantize_q4_0(float * src, void * dst, int n, int k, int qk, int64_t
     return (n/k)*row_size;
 }
 
-size_t ggml_quantize_q4_1(float * src, void * dst, int n, int k, int qk, int64_t * hist) {
+size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int qk, int64_t * hist) {
     const int nb = k / qk;
     const size_t bs = (2*sizeof(float) + sizeof(uint8_t)*qk/2);
     const size_t row_size = nb*bs;

ggml.h

@@ -745,8 +745,8 @@ enum ggml_opt_result ggml_opt(
 // quantization
 //
 
-size_t ggml_quantize_q4_0(float * src, void * dst, int n, int k, int qk, int64_t * hist);
-size_t ggml_quantize_q4_1(float * src, void * dst, int n, int k, int qk, int64_t * hist);
+size_t ggml_quantize_q4_0(const float * src, void * dst, int n, int k, int qk, int64_t * hist);
+size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int qk, int64_t * hist);
 
 //
 // system info

tests/CMakeLists.txt

@@ -1,4 +1,9 @@
-set(TEST_TARGET test-tokenizer-0)
-add_executable(${TEST_TARGET} ${TEST_TARGET}.cpp)
-target_link_libraries(${TEST_TARGET} PRIVATE llama ggml utils)
-add_test(NAME ${TEST_TARGET} COMMAND $<TARGET_FILE:${TEST_TARGET}> ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab.bin)
+function(llama_add_test source)
+    get_filename_component(TEST_TARGET ${source} NAME_WE)
+    add_executable(${TEST_TARGET} ${source})
+    target_link_libraries(${TEST_TARGET} PRIVATE llama ggml utils)
+    add_test(NAME ${TEST_TARGET} COMMAND $<TARGET_FILE:${TEST_TARGET}> ${ARGN})
+endfunction()
+
+llama_add_test(test-quantize.c)
+llama_add_test(test-tokenizer-0.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab.bin)

tests/test-quantize.c

@@ -0,0 +1,42 @@
+#include "ggml.h"
+#undef NDEBUG
+#include <assert.h>
+#include <math.h>
+
+int main(void) {
+    #define QK 32
+    float src[QK];
+    uint8_t dst[24];
+    int64_t hist[16];
+
+    for (int i = 0; i < QK; i++) {
+        src[i] = (float)(i + 1);
+    }
+
+    size_t size = ggml_quantize_q4_0(src, dst, QK, QK, QK, hist);
+    assert(size == 20);
+    float max_result = ((float *)dst)[0];
+    float max_expected = src[31] / ((1 << 3) - 1);
+    assert(max_result == max_expected);
+    for (int i = 0; i < QK; i++) {
+        uint8_t q4_result = (i % 2) ? (dst[sizeof(float) + i/2] >> 4) : (dst[sizeof(float) + i/2] & 0xF);
+        uint8_t q4_expected = roundf(src[i] / max_expected) + 8;
+        assert(q4_result == q4_expected);
+    }
+
+    size = ggml_quantize_q4_1(src, dst, QK, QK, QK, hist);
+    assert(size == 24);
+    float delta_result = ((float *)dst)[0];
+    float delta_expected = (src[31] - src[0]) / ((1 << 4) - 1);
+    assert(delta_result == delta_expected);
+    float min_result = ((float *)dst)[1];
+    float min_expected = src[0];
+    assert(min_result == min_expected);
+    for (int i = 0; i < QK; i++) {
+        uint8_t q4_result = (i % 2) ? (dst[sizeof(float)*2 + i/2] >> 4) : (dst[sizeof(float)*2 + i/2] & 0xF);
+        uint8_t q4_expected = roundf((src[i] - min_expected) / delta_expected);
+        assert(q4_result == q4_expected);
+    }
+
+    return 0;
+}