vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge commit 'e121edc432' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/release.yml
#	common/CMakeLists.txt
#	docs/function-calling.md
#	ggml/src/ggml-sycl/binbcast.cpp
#	models/templates/README.md
#	scripts/tool_bench.py
#	src/llama-kv-cache.cpp
#	tests/CMakeLists.txt
#	tests/test-chat.cpp
#	tools/mtmd/clip.h
#	tools/rpc/rpc-server.cpp
#	tools/server/README.md
This commit is contained in:
Concedo 2025-05-28 00:20:45 +08:00
commit 868cb6aff7
45 changed files with 3521 additions and 1182 deletions
Download patch file Download diff file Expand all files Collapse all files

6
src/llama-model.cpp
View file

@ -2585,7 +2585,11 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
// output
output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, 0);
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
// if output is NULL, init from the input tok embed
if (output == NULL) {
output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
}
for (int i = 0; i < n_layer; ++i) {
auto & layer = layers[i];