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 branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/docker.yml
#	Makefile
#	examples/CMakeLists.txt
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/convert.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	scripts/sync-ggml.last
This commit is contained in:
Concedo 2025-05-08 23:07:33 +08:00
commit b6220669f4
14 changed files with 410 additions and 117 deletions
Download patch file Download diff file Expand all files Collapse all files

8
src/llama-model.cpp
View file

@ -3605,7 +3605,11 @@ 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];
@ -4891,7 +4895,7 @@ struct llm_build_deci : public llm_graph_context {
}
// FFN-free layer of Llama-3_1-Nemotron-Ultra-253B
if (n_head == 0 && n_ff == 0) {
if (n_ff == 0) {
continue;
}