vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-19 16:31:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/pull_request_template.md
#	.gitignore
#	docs/backend/SYCL.md
#	docs/ops.md
#	docs/ops/WebGPU.csv
#	examples/sycl/test.sh
#	examples/sycl/win-test.bat
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/sycl_hw.cpp
#	ggml/src/ggml-sycl/sycl_hw.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
This commit is contained in:
Concedo 2026-04-25 19:06:32 +08:00
commit b31877e8ec
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama-quant.cpp
View file

@ -1285,7 +1285,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
llama_model_quantize_params llama_model_quantize_default_params() {
llama_model_quantize_params result = {
/*.nthread =*/ 0,
/*.ftype =*/ LLAMA_FTYPE_MOSTLY_Q5_1,
/*.ftype =*/ LLAMA_FTYPE_MOSTLY_Q8_0,
/*.output_tensor_type =*/ GGML_TYPE_COUNT,
/*.token_embedding_type =*/ GGML_TYPE_COUNT,
/*.allow_requantize =*/ false,