xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-30 11:57:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix links in multi-modal model contributing page (#18615)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor 2025-07-07 22:13:52 +01:00 committed by GitHub
parent 8e807cdfa4
commit 042d131f39
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 12 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/contributing/model/multimodal.md
View File

@ -819,7 +819,7 @@ Each [PromptUpdate][vllm.multimodal.processing.PromptUpdate] instance specifies
After you have defined [BaseProcessingInfo][vllm.multimodal.processing.BaseProcessingInfo] (Step 2), After you have defined [BaseProcessingInfo][vllm.multimodal.processing.BaseProcessingInfo] (Step 2),
[BaseDummyInputsBuilder][vllm.multimodal.profiling.BaseDummyInputsBuilder] (Step 3), [BaseDummyInputsBuilder][vllm.multimodal.profiling.BaseDummyInputsBuilder] (Step 3),
and [BaseMultiModalProcessor][vllm.multimodal.processing.BaseMultiModalProcessor] (Step 4), and [BaseMultiModalProcessor][vllm.multimodal.processing.BaseMultiModalProcessor] (Step 4),
decorate the model class with {meth}`MULTIMODAL_REGISTRY.register_processor <vllm.multimodal.registry.MultiModalRegistry.register_processor>` decorate the model class with [MULTIMODAL_REGISTRY.register_processor][vllm.multimodal.processing.MultiModalRegistry.register_processor]
to register them to the multi-modal registry: to register them to the multi-modal registry:
```diff ```diff

11
vllm/model_executor/models/interfaces.py
View File

@ -89,11 +89,22 @@ class SupportsMultiModal(Protocol):
) -> Tensor: ) -> Tensor:
... ...
# TODO: Remove this overload once v0 is deprecated
@overload @overload
def get_input_embeddings( def get_input_embeddings(
self, self,
input_ids: Tensor, input_ids: Tensor,
multimodal_embeddings: Optional[MultiModalEmbeddings] = None, multimodal_embeddings: Optional[MultiModalEmbeddings] = None,
) -> Tensor:
...
def get_input_embeddings(
self,
input_ids: Tensor,
multimodal_embeddings: Optional[MultiModalEmbeddings] = None,
# Only necessary so that the v0 overload is valid
# TODO: Remove attn_metadata once v0 is deprecated
attn_metadata: Optional["AttentionMetadata"] = None,
) -> Tensor: ) -> Tensor:
""" """
Returns the input embeddings merged from the text embeddings from Returns the input embeddings merged from the text embeddings from