Feat/text multi image eval - #148

Open

camilobrownpinilla wants to merge 4 commits into

multimodal-videofrom

feat/text-multi-image-eval

Commits on Jul 13, 2026

Support multi-image eval requests on video checkpoints

camilobrownpinilla
and
claude
committed
e967277
Support text-only evaluation on image and video checkpoints

camilobrownpinilla
and
claude
committed
c686ed1

Commits on Jul 22, 2026

Fix llm-judged benchmarks + clean comments
camilobrownpinilla
committed
b293b5f
Wire lmms throughput metrics through adapter
camilobrownpinilla
committed
c803dd0