Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '4a4f7e6550cf5b327ea0fb241ce7417ab46e1ace' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/ISSUE_TEMPLATE/011-bug-results.yml
#	CODEOWNERS
#	README.md
#	ci/run.sh
#	docs/development/HOWTO-add-model.md
#	grammars/README.md
#	src/llama-context.cpp
#	src/llama.cpp
#	tools/CMakeLists.txt
#	tools/completion/README.md
#	tools/llama-bench/README.md
This commit is contained in:
Concedo
2025-12-17 14:30:39 +08:00
parent 050a5b1f52 4a4f7e6550
commit c93c4c5505
27 changed files with 1152 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-quant.cpp
+1 -1
View File
@@ -599,7 +599,7 @@ 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, nullptr);
llama_model_loader ml(fname_inp, splits, use_mmap, /*check_tensors*/ true, /*no_alloc*/ false, kv_overrides, nullptr);
ml.init_mappings(false); // no prefetching
llama_model model(llama_model_default_params());