CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

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
9 changed files with 166 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama-graph.h
View File

@@ -206,7 +206,7 @@ public:
class llm_graph_input_cls : public llm_graph_input_i {
public:
llm_graph_input_cls(const llama_cparams & cparams) : cparams(cparams) {}
llm_graph_input_cls(const llama_cparams & cparams, const llm_arch arch) : cparams(cparams), arch(arch) {}
virtual ~llm_graph_input_cls() = default;
void set_input(const llama_ubatch * ubatch) override;
@@ -214,6 +214,7 @@ public:
ggml_tensor * cls; // I32 [n_batch]
const llama_cparams cparams;
const llm_arch arch;
};
class llm_graph_input_rs : public llm_graph_input_i {