From 55d2bec6de230fcf7773e4d18e85f1607f964121 Mon Sep 17 00:00:00 2001 From: intellinjun Date: Thu, 11 Jan 2024 13:57:14 +0800 Subject: [PATCH] fix format error Signed-off-by: intellinjun --- neural_speed/application/quant_whisper.cpp | 2 +- neural_speed/models/model_utils/model_utils.cpp | 1 - neural_speed/models/model_utils/quant_utils.cpp | 1 - neural_speed/models/model_utils/quant_utils.h | 4 ++-- 4 files changed, 3 insertions(+), 5 deletions(-) diff --git a/neural_speed/application/quant_whisper.cpp b/neural_speed/application/quant_whisper.cpp index 8d3503a9f..44701fd9b 100644 --- a/neural_speed/application/quant_whisper.cpp +++ b/neural_speed/application/quant_whisper.cpp @@ -31,7 +31,7 @@ int main(int argc, char** argv) { // needed to initialize f16 tables { - struct ne_init_params params = {0, NULL, false}; + struct ne_init_params params = {0, nullptr, false}; struct ne_context* ctx = ne_init(params); ne_free(ctx); } diff --git a/neural_speed/models/model_utils/model_utils.cpp b/neural_speed/models/model_utils/model_utils.cpp index 9ec04c81e..df004f32f 100644 --- a/neural_speed/models/model_utils/model_utils.cpp +++ b/neural_speed/models/model_utils/model_utils.cpp @@ -993,7 +993,6 @@ struct model_context* model_init_from_file(const char* path_model, struct model_ void model_free(struct model_context* ctx) { delete ctx; } - int model_apply_lora_from_file_internal(struct model_context* ctx, const char* path_lora, const char* path_base_model, int n_threads) { fprintf(stderr, "%s: applying lora adapter from '%s' - please wait ...\n", __func__, path_lora); diff --git a/neural_speed/models/model_utils/quant_utils.cpp b/neural_speed/models/model_utils/quant_utils.cpp index 537dbf453..db65099f4 100644 --- a/neural_speed/models/model_utils/quant_utils.cpp +++ b/neural_speed/models/model_utils/quant_utils.cpp @@ -466,7 +466,6 @@ static void model_quantize_internal(const quant_params& params, std::shared_ptr< printf("%s: quant size = %8.2f MB\n", __func__, total_size_new / 1024.0 / 1024.0); } - size_t jblas_special_quantize(const float* f32ptr, void* dstpr, int group_size, int nthread, int n, int k) { return 0; } bool model_quantize_special(std::ifstream& finp, std::ofstream& fout, const ne_ftype ftype, diff --git a/neural_speed/models/model_utils/quant_utils.h b/neural_speed/models/model_utils/quant_utils.h index efa7067ea..9ac37faf3 100644 --- a/neural_speed/models/model_utils/quant_utils.h +++ b/neural_speed/models/model_utils/quant_utils.h @@ -45,9 +45,9 @@ QUANT_API int model_quantize(const quant_params& param, std::shared_ptr quant_layer); size_t bestla_qpack(const int8_t* src_w, const float* src_scales, const int8_t* src_zps, void* dstpr, - const quant_params_internal params, int nthread, int n, int k, int* g_idx); + const quant_params_internal params, int nthread, int n, int k, int* g_idx); size_t bestla_quantize(const float* f32ptr, void* dstpr, const quant_params_internal params, int nthread, size_t n, - size_t k); + size_t k); QUANT_API bool model_quantize_special(std::ifstream& finp, std::ofstream& fout, const ne_ftype ftype, const std::vector& to_quant, const std::vector& to_skip);