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

Add explicit pooling classes for the Transformers backend (#25322)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
Harry Mellor
2025-09-30 23:07:06 +01:00
committed by GitHub
parent 9a9f48dff7
commit a388252ac4
7 changed files with 295 additions and 137 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/model_executor/models/registry.py
View File

@@ -307,9 +307,10 @@ _TRANSFORMERS_SUPPORTED_MODELS = {
}
_TRANSFORMERS_BACKEND_MODELS = {
"TransformersModel": ("transformers", "TransformersModel"),
"TransformersEmbeddingModel": ("transformers_pooling", "TransformersEmbeddingModel"), # noqa: E501
"TransformersForSequenceClassification": ("transformers_pooling", "TransformersForSequenceClassification"), # noqa: E501
"TransformersForCausalLM": ("transformers", "TransformersForCausalLM"),
"TransformersForMultimodalLM": ("transformers", "TransformersForMultimodalLM"), # noqa: E501
"TransformersForMultimodalLM": ("transformers", "TransformersForMultimodalLM"), # noqa: E501
}
# yapf: enable