ollama/mlxrunner
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
..
batch mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
cache mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
model model: add multimodal embeddings (#18820) 2026-10-06 08:08:38 -07:00
nn mlx: speed up Qwen 3.8 prompt processing (#18550) 2026-09-22 17:53:23 -07:00
sample
tokenizer mlx: match publisher tokenizer semantics (#18779) 2026-10-04 07:45:15 -07:00
xgrammar xgrammar: add standalone CMake project for native library (#18611) 2026-09-23 11:20:59 -07:00
cache_trie.go
cache_trie_test.go
client.go model: add multimodal embeddings (#18820) 2026-10-06 08:08:38 -07:00
client_score.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
client_score_test.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
client_test.go server: apply structured outputs in a single pass on thinking models 2026-09-22 11:24:11 -07:00
dflash.go
dflash_test.go
embed.go model: add multimodal embeddings (#18820) 2026-10-06 08:08:38 -07:00
embed_test.go model: add multimodal embeddings (#18820) 2026-10-06 08:08:38 -07:00
grammar.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
grammar_mask_test.go
grammar_test.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
media.go
media_test.go
mtp.go
mtp_test.go server: apply structured outputs in a single pass on thinking models 2026-09-22 11:24:11 -07:00
pipeline.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
pipeline_test.go
prefix_cache.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
prefix_cache_scenario_test.go
prefix_cache_test.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
runner.go model: add multimodal embeddings (#18820) 2026-10-06 08:08:38 -07:00
score.go Reduce model lookup and MLX decision request overhead (#18806) 2026-10-05 17:34:41 -07:00
score_hidden_test.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
score_test.go Reduce model lookup and MLX decision request overhead (#18806) 2026-10-05 17:34:41 -07:00
server.go model: add multimodal embeddings (#18820) 2026-10-06 08:08:38 -07:00
speculate.go
speculate_depth.go
speculate_depth_test.go
speculate_stats.go
status_memory.go
status_memory_test.go
utf8_buffer.go
utf8_buffer_test.go
verify.go
verify_test.go