Add OmniMRotaryEmbedding for multimodal position computation

- Introduced OmniMRotaryEmbedding to extend MRotaryEmbedding with methods for computing input positions across various multimodal scenarios, including image, video, and audio inputs.
- Updated patch.py to replace the original MRotaryEmbedding with OmniMRotaryEmbedding in the module patching logic.
- Created new files for the OmniMRotaryEmbedding implementation and its associated methods.

Signed-off-by: [Your Name] <[Your Email]>

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
tzhouam committed 2026-01-30 10:03:02 +00:00
1 parent 3208afd82b
commit 7aea8e8d91
17 files changed
+744 -57

No files matched your search

+2 -3
View File
@@ -4,13 +4,12 @@ from vllm.inputs.parse import (
ParsedStrPrompt,
ParsedTextPrompt,
ParsedTokensPrompt,
SingletonPrompt,
)
from vllm_omni.inputs.data import OmniSingletonPrompt
def parse_singleton_prompt_omni(
prompt: OmniSingletonPrompt,
prompt: SingletonPrompt,
) -> ParsedSingletonPrompt:
"""Parse a singleton prompt into a typed parsed prompt.