ollama/mlxrunner/model
Patrick Devine 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
..
architectures model: add multimodal embeddings (#18820) 2026-10-06 08:08:38 -07:00
audio
clef mlx: Decision model improvements (#18776) 2026-10-03 17:48:08 -07:00
cohere2_moe mlxrunner, cmd, server: fold three small packages into their users 2026-09-16 14:06:08 -07:00
dflash mlxrunner, cmd, server: fold three small packages into their users 2026-09-16 14:06:08 -07:00
gemma4 model: add multimodal embeddings (#18820) 2026-10-06 08:08:38 -07:00
gemma4embedding model: add multimodal embeddings (#18820) 2026-10-06 08:08:38 -07:00
glimmer mlxrunner, cmd, server: fold three small packages into their users 2026-09-16 14:06:08 -07:00
glm4_moe_lite mlxrunner, cmd, server: fold three small packages into their users 2026-09-16 14:06:08 -07:00
laguna mlxrunner, cmd, server: fold three small packages into their users 2026-09-16 14:06:08 -07:00
laya mlx: Decision model improvements (#18776) 2026-10-03 17:48:08 -07:00
llama mlxrunner, cmd, server: fold three small packages into their users 2026-09-16 14:06:08 -07:00
nemotron_h nemotron_h: add MLX vision support (#17714) 2026-09-17 16:29:14 -07:00
qwen3 mlxrunner, cmd, server: fold three small packages into their users 2026-09-16 14:06:08 -07:00
qwen3_5 mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
qwen3_5_moe mlxrunner, cmd, server: fold three small packages into their users 2026-09-16 14:06:08 -07:00
qwen4_exp mlxrunner, cmd, server: fold three small packages into their users 2026-09-16 14:06:08 -07:00
strands mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
embedding.go
embedding_test.go
globalscale.go mlxrunner: lay out model by contract, checkpoint and construction 2026-09-16 14:06:08 -07:00
globalscale_test.go mlxrunner: lay out model by contract, checkpoint and construction 2026-09-16 14:06:08 -07:00
linear.go
media.go mlxrunner, cmd, server: fold three small packages into their users 2026-09-16 14:06:08 -07:00
model.go mlxrunner: lay out model by contract, checkpoint and construction 2026-09-16 14:06:08 -07:00
quant.go mlxrunner: lay out model by contract, checkpoint and construction 2026-09-16 14:06:08 -07:00
root.go mlxrunner: lay out model by contract, checkpoint and construction 2026-09-16 14:06:08 -07:00
score.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00