Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Add geglu activation function #14074

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 9, 2025
Merged

Add geglu activation function #14074

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 22 additions & 0 deletions src/llama-graph.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -659,6 +659,28 @@ ggml_tensor * llm_graph_context::build_ffn(
cur = ggml_mul(ctx0, x0, x1);
cb(cur, "ffn_mul", il);
} break;
case LLM_FFN_GEGLU:
{
// Split into two equal parts
int64_t split_point = cur->ne[0] / 2;
ggml_tensor * output_ffn_up = ggml_cont(ctx0, ggml_view_2d(
ctx0, cur, split_point,
cur->ne[1], cur->nb[1], 0
));
ggml_tensor * output_ffn_gate = ggml_cont(ctx0, ggml_view_2d(
ctx0, cur, split_point,
cur->ne[1], cur->nb[1],
split_point * ggml_element_size(cur)
));

// Apply GELU activation function to the first part
output_ffn_up = ggml_gelu(ctx0, output_ffn_up);
cb(output_ffn_up, "ffn_gelu", il);

// Element-wise multiplication between the activated part and the gate part
cur = ggml_mul(ctx0, output_ffn_up, output_ffn_gate);
cb(cur, "ffn_geglu", il);
} break;
}

if (gate && type_gate == LLM_FFN_PAR) {
Expand Down
1 change: 1 addition & 0 deletions src/llama-graph.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@ enum llm_ffn_op_type {
LLM_FFN_RELU,
LLM_FFN_RELU_SQR,
LLM_FFN_SWIGLU,
LLM_FFN_GEGLU,
};

enum llm_ffn_gate_type {
Expand Down
Loading