Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-08 05:49:10 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '451ef08432d1f7d3d6071d4006cbbeda21dcfbec' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build.yml
#	README.md
#	docs/ops.md
#	docs/ops/Vulkan.csv
#	src/llama-model-loader.cpp
#	src/llama-model.cpp
#	src/llama.cpp
#	tests/CMakeLists.txt
#	tests/peg-parser/test-basic.cpp
#	tests/peg-parser/test-json-parser.cpp
#	tests/peg-parser/test-python-dict-parser.cpp
#	tests/peg-parser/test-unicode.cpp
#	tests/test-chat-auto-parser.cpp
#	tests/test-chat-peg-parser.cpp
#	tests/test-chat.cpp
#	tools/CMakeLists.txt
This commit is contained in:
Concedo
2026-03-13 23:33:37 +08:00
parent d2c911884d 451ef08432
commit 04915d99ee
36 changed files with 1001 additions and 725 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-quant.cpp
+3 -2
View File
@@ -556,7 +556,8 @@ 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, /*use_direct_io*/ false, /*check_tensors*/ true, /*no_alloc*/ false, kv_overrides, nullptr);
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);
ml.init_mappings(false); // no prefetching
llama_model model(llama_model_default_params());
@@ -596,7 +597,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
}
// copy the KV pairs from the input file
gguf_set_kv (ctx_out.get(), ml.meta.get());
gguf_set_kv (ctx_out.get(), ml.metadata);
gguf_set_val_u32(ctx_out.get(), "general.quantization_version", GGML_QNT_VERSION); // TODO: use LLM_KV
gguf_set_val_u32(ctx_out.get(), "general.file_type", ftype); // TODO: use LLM_KV