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 branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/s390x.Dockerfile
#	.dockerignore
#	.github/workflows/docker.yml
#	.github/workflows/release.yml
#	docs/android.md
#	ggml/src/ggml-cpu/amx/mmq.cpp
#	ggml/src/ggml-hexagon/htp/ssm-conv.c
#	tests/peg-parser/test-gbnf-generation.cpp
#	tests/test-arg-parser.cpp
#	tests/test-chat.cpp
#	tests/test-jinja.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2026-06-22 18:23:59 +08:00
parent dfa1c573c4 d0f9d2e5ac
commit 3090ae0bf7
53 changed files with 1575 additions and 732 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-quant.cpp
+2 -2
View File
@@ -934,8 +934,8 @@ 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.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
gguf_set_val_u32(ctx_out.get(), ml.llm_kv(LLM_KV_GENERAL_QUANTIZATION_VERSION).c_str(), GGML_QNT_VERSION);
gguf_set_val_u32(ctx_out.get(), ml.llm_kv(LLM_KV_GENERAL_FILE_TYPE).c_str(), ftype);
// Remove split metadata
gguf_remove_key(ctx_out.get(), ml.llm_kv(LLM_KV_SPLIT_NO).c_str());