vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-13 10:29:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	docs/backend/CANN.md
#	docs/multimodal/minicpmo2.6.md
#	docs/multimodal/minicpmv2.5.md
#	docs/multimodal/minicpmv2.6.md
#	examples/speculative-simple/speculative-simple.cpp
#	ggml/cmake/ggml-config.cmake.in
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/repack.cpp
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/add.cl
#	ggml/src/ggml-opencl/kernels/mul.cl
#	scripts/compare-commits.sh
#	scripts/compare-llama-bench.py
#	scripts/sync-ggml.last
#	tools/server/README.md
This commit is contained in:
Concedo 2025-08-02 10:25:10 +08:00
commit f430916a71
57 changed files with 6028 additions and 731 deletions
Download patch file Download diff file Expand all files Collapse all files

6
src/llama-quant.cpp
View file

@ -878,9 +878,10 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
// get more optimal quantization type based on the tensor shape, layer, etc.
if (!params->pure && ggml_is_quantized(default_type)) {
int fallback = qs.n_fallback;
new_type = llama_tensor_get_type(qs, new_type, tensor, ftype);
// unless the user specifies a type
if (params->tensor_types) {
// unless the user specifies a type, and the tensor geometry will not require fallback quantisation
if (params->tensor_types && qs.n_fallback - fallback == 0) {
const std::vector<tensor_quantization> & tensor_types = *static_cast<const std::vector<tensor_quantization> *>(params->tensor_types);
const std::string tensor_name(tensor->name);
for (const auto & [tname, qtype] : tensor_types) {
@ -893,7 +894,6 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
}
}
}
if (params->token_embedding_type < GGML_TYPE_COUNT && strcmp(tensor->name, "token_embd.weight") == 0) {
new_type = params->token_embedding_type;
}