llama : add support for qwen3 reranker (#15824)

2025-09-25 03:53:09 -05:00
parent dfcd53f7ec
commit b5bd037832
9 changed files with 166 additions and 78 deletions
--- a/src/llama-arch.cpp
+++ b/src/llama-arch.cpp
@@ -721,6 +721,7 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
+            { LLM_TENSOR_CLS_OUT,         "cls.output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_Q_NORM,     "blk.%d.attn_q_norm" },