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

[Multimodal] Always enable hashing mm data (#23308)

Browse Source 
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Roger Wang
2025-08-21 07:23:28 -07:00
committed by GitHub
parent f8daddcc4c
commit 79f05e4436
15 changed files with 94 additions and 148 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/model_executor/models/paligemma.py
View File

@@ -194,10 +194,9 @@ class PaliGemmaMultiModalProcessor(
mm_data: MultiModalDataDict,
hf_processor_mm_kwargs: Mapping[str, object],
tokenization_kwargs: Optional[Mapping[str, object]] = None,
return_mm_hashes: bool = False,
) -> MultiModalInputs:
mm_inputs = super().apply(prompt, mm_data, hf_processor_mm_kwargs,
tokenization_kwargs, return_mm_hashes)
tokenization_kwargs)
prompt_token_ids = mm_inputs["prompt_token_ids"]
tokenizer = self.info.get_tokenizer()