Patrick DevineandGitHub efe43c5561 model: add multimodal embeddings (#18820) ...

Implements the EmbeddingGemma2Model architecture on the MLX runner: 24-layer
bidirectional text encoder with PLE, shared gemma4 vision/audio towers,
mean-pool + L2 output. /api/embed accepts per-item media via input dicts.

2026-10-06 08:08:38 -07:00

..

forward.go

…

gemma4embedding_test.go

…

gemma4embedding_towers_test.go

…

gemma4embedding.go

…