diff options
Diffstat (limited to 'tests')
| -rw-r--r-- | tests/test-backend-ops.cpp | 1 | ||||
| -rw-r--r-- | tests/test-quantize-fns.cpp | 13 | ||||
| -rw-r--r-- | tests/test-quantize-perf.cpp | 2 |
3 files changed, 13 insertions, 3 deletions
diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp index 775147d4..b328b19b 100644 --- a/tests/test-backend-ops.cpp +++ b/tests/test-backend-ops.cpp @@ -1890,6 +1890,7 @@ static bool test_backend(ggml_backend_t backend, test_mode mode, const char * op GGML_TYPE_Q4_K, GGML_TYPE_Q5_K, GGML_TYPE_Q6_K, GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, + GGML_TYPE_IQ3_XXS, }; // unary ops diff --git a/tests/test-quantize-fns.cpp b/tests/test-quantize-fns.cpp index 31a78c63..43df8022 100644 --- a/tests/test-quantize-fns.cpp +++ b/tests/test-quantize-fns.cpp @@ -17,7 +17,9 @@ constexpr float MAX_QUANTIZATION_REFERENCE_ERROR = 0.0001f; constexpr float MAX_QUANTIZATION_TOTAL_ERROR = 0.002f; constexpr float MAX_QUANTIZATION_TOTAL_ERROR_2BITS = 0.0075f; constexpr float MAX_QUANTIZATION_TOTAL_ERROR_3BITS = 0.0040f; +constexpr float MAX_QUANTIZATION_TOTAL_ERROR_3BITS_XXS = 0.0050f; constexpr float MAX_DOT_PRODUCT_ERROR = 0.02f; +constexpr float MAX_DOT_PRODUCT_ERROR_LOWBIT = 0.04f; static const char* RESULT_STR[] = {"ok", "FAILED"}; @@ -135,18 +137,21 @@ int main(int argc, char * argv[]) { } const ggml_type ei = (ggml_type)i; + if (ei == GGML_TYPE_IQ2_XXS || ei == GGML_TYPE_IQ2_XS) { printf("Skip %s due to missing quantization functionality\n", ggml_type_name(ei)); continue; } printf("Testing %s\n", ggml_type_name((ggml_type) i)); + ggml_quantize_init(ei); if (qfns.from_float && qfns.to_float) { const float total_error = total_quantization_error(qfns, test_size, test_data.data()); const float max_quantization_error = - type == GGML_TYPE_Q2_K ? MAX_QUANTIZATION_TOTAL_ERROR_2BITS : - type == GGML_TYPE_Q3_K ? MAX_QUANTIZATION_TOTAL_ERROR_3BITS : MAX_QUANTIZATION_TOTAL_ERROR; + type == GGML_TYPE_Q2_K ? MAX_QUANTIZATION_TOTAL_ERROR_2BITS : + type == GGML_TYPE_Q3_K ? MAX_QUANTIZATION_TOTAL_ERROR_3BITS : + type == GGML_TYPE_IQ3_XXS ? MAX_QUANTIZATION_TOTAL_ERROR_3BITS_XXS : MAX_QUANTIZATION_TOTAL_ERROR; failed = !(total_error < max_quantization_error); num_failed += failed; if (failed || verbose) { @@ -161,7 +166,9 @@ int main(int argc, char * argv[]) { } const float vec_dot_error = dot_product_error(qfns, test_size, test_data.data(), test_data2.data()); - failed = !(vec_dot_error < MAX_DOT_PRODUCT_ERROR); + const float max_allowed_error = type == GGML_TYPE_Q2_K || type == GGML_TYPE_IQ2_XS || type == GGML_TYPE_IQ2_XXS || + type == GGML_TYPE_IQ3_XXS ? MAX_DOT_PRODUCT_ERROR_LOWBIT : MAX_DOT_PRODUCT_ERROR; + failed = !(vec_dot_error < max_allowed_error); num_failed += failed; if (failed || verbose) { printf("%5s dot product error: %s (%f)\n", ggml_type_name(type), RESULT_STR[failed], vec_dot_error); diff --git a/tests/test-quantize-perf.cpp b/tests/test-quantize-perf.cpp index 09d410b7..8ec81734 100644 --- a/tests/test-quantize-perf.cpp +++ b/tests/test-quantize-perf.cpp @@ -278,6 +278,8 @@ int main(int argc, char * argv[]) { if (qfns.from_float && qfns.to_float) { printf("%s\n", ggml_type_name(type)); + ggml_quantize_init(type); + if (params.op_quantize_row_q_reference) { printf(" quantize_row_q_reference\n"); for (size_t size : params.test_sizes) { |