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

model : qwen3vl reranker text support (#20332)

Browse source 
* model : fix qwen3vl reranker support

* Remove CLS_OUT

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Vinicios Lugli 2026-03-10 19:40:14 -03:00 • committed by GitHub
parent 10e5b148b0
commit 4d99d45084
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 23 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

1
src/llama-arch.cpp
View file

@ -1087,6 +1087,7 @@ static std::set<llm_tensor> llm_get_tensor_names(llm_arch arch) {
LLM_TENSOR_TOKEN_EMBD,
LLM_TENSOR_OUTPUT_NORM,
LLM_TENSOR_OUTPUT,
LLM_TENSOR_CLS_OUT,
LLM_TENSOR_ATTN_NORM,
LLM_TENSOR_ATTN_Q,
LLM_TENSOR_ATTN_Q_NORM,