vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-08 18:30:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	docs/build-s390x.md
#	docs/ops.md
#	docs/ops/zDNN.csv
#	ggml/include/ggml-zdnn.h
#	ggml/src/ggml-sycl/binbcast.cpp
#	ggml/src/ggml-sycl/concat.cpp
#	ggml/src/ggml-sycl/conv.cpp
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/cpy.cpp
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/dpct/helper.hpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/getrows.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/gla.cpp
#	ggml/src/ggml-sycl/im2col.cpp
#	ggml/src/ggml-sycl/mmq.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/norm.cpp
#	ggml/src/ggml-sycl/rope.cpp
#	ggml/src/ggml-sycl/set_rows.cpp
#	ggml/src/ggml-sycl/softmax.cpp
#	ggml/src/ggml-sycl/tsembd.cpp
#	ggml/src/ggml-sycl/wkv.cpp
#	ggml/src/ggml-zdnn/ggml-zdnn-impl.h
#	ggml/src/ggml-zdnn/ggml-zdnn.cpp
#	tools/llama-bench/llama-bench.cpp
This commit is contained in:
Concedo 2025-09-13 12:25:30 +08:00
commit 1dbd2fc259
14 changed files with 406 additions and 68 deletions
Download patch file Download diff file Expand all files Collapse all files

6
src/llama-quant.cpp
View file

@ -923,7 +923,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
new_type = tensor->type;
new_data = tensor->data;
new_size = ggml_nbytes(tensor);
LLAMA_LOG_INFO("size = %8.3f MB\n", ggml_nbytes(tensor)/1024.0/1024.0);
LLAMA_LOG_INFO("size = %8.3f MiB\n", ggml_nbytes(tensor)/1024.0/1024.0);
} else {
const int64_t nelements = ggml_nelements(tensor);
@ -1040,8 +1040,8 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
}
close_ofstream();
LLAMA_LOG_INFO("%s: model size = %8.2f MB\n", __func__, total_size_org/1024.0/1024.0);
LLAMA_LOG_INFO("%s: quant size = %8.2f MB\n", __func__, total_size_new/1024.0/1024.0);
LLAMA_LOG_INFO("%s: model size = %8.2f MiB\n", __func__, total_size_org/1024.0/1024.0);
LLAMA_LOG_INFO("%s: quant size = %8.2f MiB\n", __func__, total_size_new/1024.0/1024.0);
if (qs.n_fallback > 0) {
LLAMA_LOG_WARN("%s: WARNING: %d of %d tensor(s) required fallback quantization\n",