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

[Multimodal] Generate mm_hash based on request metadata when caching is turned off (#23690)

Browse Source 
Signed-off-by: Roger Wang <hey@rogerw.io>
This commit is contained in:
Roger Wang
2025-08-27 13:24:31 -07:00
committed by GitHub
parent 0585a9e73c
commit 8bf6266a17
12 changed files with 179 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/model_executor/models/paligemma.py
View File

@@ -203,9 +203,13 @@ class PaliGemmaMultiModalProcessor(
mm_data: MultiModalDataDict,
hf_processor_mm_kwargs: Mapping[str, object],
tokenization_kwargs: Optional[Mapping[str, object]] = None,
mm_hash_overrides: Optional[dict[str, list[str]]] = None,
) -> MultiModalInputs:
mm_inputs = super().apply(prompt, mm_data, hf_processor_mm_kwargs,
tokenization_kwargs)
mm_inputs = super().apply(prompt,
mm_data,
hf_processor_mm_kwargs,
tokenization_kwargs,
mm_hash_overrides=mm_hash_overrides)
prompt_token_ids = mm_inputs["prompt_token_ids"]
tokenizer = self.info.get_tokenizer()