vllm/model_executor/models/gemma3n_mm.py · bd51f78e39e0ea80b1d3bfbb17d24f40b1f62f6c · OpenDAS / vllm_cscc

"tests/entrypoints/llm/test_mm_embeds_only.py" did not exist on "785cf28ffffeddeecf79018074a222b7c5938f9c"

[Bugfix] Merge MM embeddings by index instead of token IDs (#16229) · 27d7638b

Cyrus Leung authored Sep 27, 2025


Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

27d7638b

gemma3n_mm.py 30.1 KB

Replace gemma3n_mm.py