biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Bugfix] Fix normalize still being passed to PoolerConfig (#33794)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-02-04 23:56:02 +08:00
committed by GitHub
parent 711edaf0d0
commit 80f921ba4b
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/models/language/pooling/test_embedding.py
View File

@@ -54,7 +54,7 @@ def test_models(
vllm_extra_kwargs = {}
if model == "ssmits/Qwen2-7B-Instruct-embed-base":
vllm_extra_kwargs["pooler_config"] = PoolerConfig(
seq_pooling_type="MEAN", normalize=False
seq_pooling_type="MEAN", use_activation=False
)
max_model_len: int | None = 512

4
vllm/entrypoints/llm.py
View File

@@ -174,8 +174,8 @@ class LLM:
multi-modal processor obtained from `AutoProcessor.from_pretrained`.
The available overrides depend on the model that is being run.
For example, for Phi-3-Vision: `{"num_crops": 4}`.
pooler_config: Initialize non-default pooling config for the pooling
model. e.g. `PoolerConfig(seq_pooling_type="MEAN", normalize=False)`.
pooler_config: Initialize non-default pooling config for the pooling model,
e.g., `PoolerConfig(seq_pooling_type="MEAN", use_activation=False)`.
compilation_config: Either an integer or a dictionary. If it is an
integer, it is used as the mode of compilation optimization. If it
is a dictionary, it can specify the full compilation configuration.