Enable headless models for pooling in the Transformers backend (#21767)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-08-01 10:31:29 -07:00
committed by GitHub
parent ac45c44d98
commit 38c8bce8b6
5 changed files with 44 additions and 9 deletions
+1
View File
@@ -525,6 +525,7 @@ _SPECULATIVE_DECODING_EXAMPLE_MODELS = {
}
_TRANSFORMERS_BACKEND_MODELS = {
"TransformersModel": _HfExamplesInfo("Qwen/Qwen3-Embedding-0.6B"),
"TransformersForCausalLM": _HfExamplesInfo("hmellor/Ilama-3.2-1B", trust_remote_code=True), # noqa: E501
"TransformersForMultimodalLM": _HfExamplesInfo("OpenGVLab/InternVL3-1B-hf"),
}