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

1
src/llama-arch.cpp
View file

@ -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" },