CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama-context: only warn on pooling_type when user specified (#16674)

Browse Source 
The unexpeced pooling_type warning was incorrectly shown when users did not
specify the --pooling-type parameter. In this case, the parameter
defaults to `LLAMA_POOLING_TYPE_UNSPECIFIED (-1)`, and the code
automatically applies the model's default pooling type.

Example of spurious warning:
```
$ llama-embedding -hf ggml-org/bge-m3-Q8_0-GGUF -p "hello"
...
llama_init_from_model: model default pooling_type is [2], but [-1] was specified
...
```

This fix ensures the warning only appears when users explicitly specify
a pooling type that differs from the model's default (e.g., using
--pooling-type mean on a model that expects CLS pooling).
This commit is contained in:
takuya kodama
2025-10-20 15:44:21 +08:00
committed by GitHub
parent 0398752dd4
commit 7062dd8460
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama-context.cpp
View File

@@ -2346,7 +2346,8 @@ llama_context * llama_init_from_model(
return nullptr;
}
if (params.pooling_type != model->hparams.pooling_type) {
if (params.pooling_type != LLAMA_POOLING_TYPE_UNSPECIFIED &&
params.pooling_type != model->hparams.pooling_type) {
//user-specified pooling-type is different from the model default
LLAMA_LOG_WARN("%s: model default pooling_type is [%d], but [%d] was specified\n", __func__,
model->hparams.pooling_type, params.pooling_type);