ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-13 04:28:07 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2025-02-03 22:42:26 +02:00
parent cff8868b5f
commit 3f91832352
17 changed files with 582 additions and 232 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/talk-llama/llama-quant.cpp
View File

@ -526,7 +526,8 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
kv_overrides = v->data();
}
llama_model_loader ml(fname_inp, use_mmap, /*check_tensors*/ true, kv_overrides);
std::vector<std::string> splits = {};
llama_model_loader ml(fname_inp, splits, use_mmap, /*check_tensors*/ true, kv_overrides);
ml.init_mappings(false); // no prefetching
llama_model model(llama_model_default_params());