tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 04:35:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : add option to override model tensor buffers (#11397)

Browse Source 
* llama : add option to override tensor buffers

* ggml : fix possible underflow in ggml_nbytes
This commit is contained in:
Diego Devesa
2025-04-02 14:52:01 +02:00
committed by GitHub
parent a10b36c91a
commit e0e912f49b
12 changed files with 108 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-quant.cpp
View File

@ -527,7 +527,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
}
std::vector<std::string> splits = {};
llama_model_loader ml(fname_inp, splits, use_mmap, /*check_tensors*/ true, kv_overrides);
llama_model_loader ml(fname_inp, splits, use_mmap, /*check_tensors*/ true, kv_overrides, nullptr);
ml.init_mappings(false); // no prefetching
llama_model model(llama_model_default_params());