ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-28 02:11:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Be able to set reduce op data type for split mode "graph" (#1087)

Browse Source 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-12-24 14:01:29 +01:00
committed by GitHub
parent 2421a7e12b
commit 1ace5b7526
7 changed files with 23 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/llama-load-tensors.cpp
View File

@@ -2265,7 +2265,6 @@ bool create_tensors_helper::create_cohere2_tensors(const LLM_TN & tn) {
for (int i = 0; i < n_layer; ++i) {
auto & layer = model.layers[i];
ggml_context * ctx_split = ctx_for_layer_split(i);
ggml_context * ctx_layer = ctx_for_layer(i);
layer.attn_norm = create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_NORM, "weight", i), { n_embd }, 0);