tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 20:25:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : gemma3 : use output tensor if it exists in model weight (#12506)

Browse Source 
* llama : gemma3 : use output tensor if it exists in model weight

* also add to the llm_tensor_names
This commit is contained in:
Xuan-Son Nguyen
2025-03-22 23:28:19 +01:00
committed by GitHub
parent ba932dfb50
commit fbdfefe74e
3 changed files with 8 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/llama-model.cpp
View File

@ -2571,7 +2571,12 @@ 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_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED); // same as tok_embd, duplicated to allow offloading
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];