thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

llama : add support for qwen3 reranker (#15824)

Browse source
This commit is contained in:
Douglas Hanley 2025-09-25 03:53:09 -05:00 • committed by GitHub
parent dfcd53f7ec
commit b5bd037832
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 166 additions and 78 deletions
Download patch file Download diff file Expand all files Collapse all files

3
src/llama-model.cpp
View file

@ -3167,6 +3167,9 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
}
// output rerank head
cls_out = create_tensor(tn(LLM_TENSOR_CLS_OUT, "weight"), {n_embd, hparams.n_cls_out}, TENSOR_NOT_REQUIRED);
for (int i = 0; i < n_layer; ++i) {
auto & layer = layers[i];