Skip to content
This repository has been archived by the owner on Aug 30, 2024. It is now read-only.

Commit

Permalink
fix format error
Browse files Browse the repository at this point in the history
Signed-off-by: intellinjun <[email protected]>
  • Loading branch information
intellinjun committed Jan 11, 2024
1 parent ae13e09 commit 55d2bec
Show file tree
Hide file tree
Showing 4 changed files with 3 additions and 5 deletions.
2 changes: 1 addition & 1 deletion neural_speed/application/quant_whisper.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -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);
}
Expand Down
1 change: 0 additions & 1 deletion neural_speed/models/model_utils/model_utils.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -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);
Expand Down
1 change: 0 additions & 1 deletion neural_speed/models/model_utils/quant_utils.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -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,
Expand Down
4 changes: 2 additions & 2 deletions neural_speed/models/model_utils/quant_utils.h
Original file line number Diff line number Diff line change
Expand Up @@ -45,9 +45,9 @@

QUANT_API int model_quantize(const quant_params& param, std::shared_ptr<quant_layer_base> 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<std::string>& to_quant,
const std::vector<std::string>& to_skip);
Expand Down

0 comments on commit 55d2bec

Please sign in to comment.