vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/musa.Dockerfile
#	.github/workflows/build.yml
#	README.md
#	ci/README.md
#	docs/docker.md
#	examples/lookahead/lookahead.cpp
#	examples/lookup/lookup.cpp
#	examples/parallel/parallel.cpp
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	tests/test-arg-parser.cpp
This commit is contained in:
Concedo 2025-05-21 23:12:22 +08:00
commit da7fd4aa57
22 changed files with 270 additions and 384 deletions
Download patch file Download diff file Expand all files Collapse all files

17
src/llama-model.cpp
View file

@ -4903,8 +4903,21 @@ struct llm_build_llama_iswa : public llm_graph_context {
ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
cb(ffn_inp, "ffn_inp", il);
{
// llama4 MoE
// feed-forward network (non-MoE)
if (model.layers[il].ffn_gate_inp == nullptr) {
cur = build_norm(ffn_inp,
model.layers[il].ffn_norm, NULL,
LLM_NORM_RMS, il);
cb(cur, "ffn_norm", il);
cur = build_ffn(cur,
model.layers[il].ffn_up, model.layers[il].ffn_up_b, NULL,
model.layers[il].ffn_gate, model.layers[il].ffn_gate_b, NULL,
model.layers[il].ffn_down, model.layers[il].ffn_down_b, NULL,
NULL,
LLM_FFN_SILU, LLM_FFN_PAR, il);
cb(cur, "ffn_out", il);
} else {
ggml_tensor * ffn_inp_normed = build_norm(ffn_inp,
model.layers[il].ffn_norm, NULL,
LLM_NORM_RMS, il);