FusedMoE support for the Transformers backend (#22650)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-10-03 07:12:15 +01:00
committed by GitHub
parent 39b643dc1a
commit 10d765482d
10 changed files with 485 additions and 91 deletions

View File

@@ -307,10 +307,14 @@ _TRANSFORMERS_SUPPORTED_MODELS = {
}
_TRANSFORMERS_BACKEND_MODELS = {
"TransformersEmbeddingModel": ("transformers_pooling", "TransformersEmbeddingModel"), # noqa: E501
"TransformersForSequenceClassification": ("transformers_pooling", "TransformersForSequenceClassification"), # noqa: E501
"TransformersForCausalLM": ("transformers", "TransformersForCausalLM"),
"TransformersForMultimodalLM": ("transformers", "TransformersForMultimodalLM"), # noqa: E501
"TransformersMoEForCausalLM": ("transformers_moe", "TransformersMoEForCausalLM"), # noqa: E501
"TransformersMoEForMultimodalLM": ("transformers_moe", "TransformersMoEForMultimodalLM"), # noqa: E501
"TransformersEmbeddingModel": ("transformers_pooling", "TransformersEmbeddingModel"), # noqa: E501
"TransformersForSequenceClassification": ("transformers_pooling", "TransformersForSequenceClassification"), # noqa: E501
"TransformersMoEForSequenceClassification": ("transformers_pooling", "TransformersMoEForSequenceClassification"), # noqa: E501
"TransformersMoEEmbeddingModel": ("transformers_pooling", "TransformersMoEEmbeddingModel"), # noqa: E501
}
# yapf: enable