Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-11 23:59:20 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/build.yml
#	.github/workflows/copilot-setup-steps.yml
#	.github/workflows/gguf-publish.yml
#	ci/run.sh
#	docs/backend/OPENVINO.md
#	examples/llama.android/lib/src/main/cpp/ai_chat.cpp
#	ggml/src/ggml-sycl/add-id.cpp
#	requirements/requirements-pydantic.txt
#	tests/test-gguf.cpp
#	tests/test-jinja.cpp
#	tests/test-llama-archs.cpp
#	tools/gguf-split/README.md
#	tools/llama-bench/llama-bench.cpp
This commit is contained in:
Concedo
2026-03-28 01:18:20 +08:00
parent 2cdf02102e 9c600bcd4b
commit 3ec6381123
28 changed files with 342 additions and 124 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-quant.cpp
+1 -1
View File
@@ -861,7 +861,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
std::vector<std::string> splits = {};
llama_model_loader ml(/*metadata*/ nullptr, /*set_tensor_data*/ nullptr, /*set_tensor_data_ud*/ nullptr,
fname_inp, splits, use_mmap, /*use_direct_io*/ false, /*check_tensors*/ true, /*no_alloc*/ false, kv_overrides, nullptr);
fname_inp, splits, /*file*/ nullptr, use_mmap, /*use_direct_io*/ false, /*check_tensors*/ true, /*no_alloc*/ false, kv_overrides, nullptr);
ml.init_mappings(false); // no prefetching
llama_model model(llama_model_default_params());