Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-04 02:37:27 +02:00
Code Issues Packages Projects Releases Wiki Activity

models : fix plamo2 graph

Browse Source
This commit is contained in:
Georgi Gerganov
2026-09-03 17:19:51 +03:00
parent 07e067b0f5
commit abbd687cb7
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/plamo2.cpp
+5 -5
View File
@@ -142,6 +142,11 @@ llama_model_plamo2::graph::graph(const llama_model & model, const llm_graph_para
cur = build_plamo2_attn_layer(inp_hybrid->get_attn(), inp_pos, cur, model, il);
}
if (il == n_layer - 1 && inp_out_ids) {
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
residual = ggml_get_rows(ctx0, residual, inp_out_ids);
}
// post_mixer_norm
cur = build_norm(cur, model.layers[il].attn_post_norm, NULL, LLM_NORM_RMS, il);
cb(cur, "attn_post_norm", il);
@@ -167,11 +172,6 @@ llama_model_plamo2::graph::graph(const llama_model & model, const llm_graph_para
cur = build_norm(cur, model.layers[il].ffn_post_norm, NULL, LLM_NORM_RMS, il);
cb(cur, "ffn_post_norm", il);
if (il == n_layer - 1 && inp_out_ids) {
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
residual = ggml_get_rows(ctx0, residual, inp_out_ids);
}
// residual connection
cur = ggml_add(ctx0, cur, residual);
cb(cur, "ffn_residual", il);