Patrick Devine d727aacd04 mlx: quantized embeddings, fast SwiGLU, and runtime fixes (#14884) ...

Add QuantizedEmbedding and EmbeddingLayer interface so models can
use quantized embedding weights and expose tied output projections.
This change updates gemma3, glm4_moe_lite, llama, qwen3, and qwen3_5
to use the new interface.

2026-03-17 11:21:38 -07:00

..

agent

x/cmd: enable web search and web fetch with flag (#13690)

2026-01-12 13:59:40 -08:00

cmd

Reapply "don't require pulling stubs for cloud models" again (#14608)

2026-03-06 14:27:47 -08:00

create

mlx: add prequantized tensor packing + changes for qwen35 (#14878)

2026-03-17 11:21:18 -07:00

imagegen

mlx: add prequantized tensor packing + changes for qwen35 (#14878)

2026-03-17 11:21:18 -07:00

mlxrunner

mlx: quantized embeddings, fast SwiGLU, and runtime fixes (#14884)

2026-03-17 11:21:38 -07:00

models

mlx: quantized embeddings, fast SwiGLU, and runtime fixes (#14884)

2026-03-17 11:21:38 -07:00

server

bugfix: display the parameter count correctly in mlx for ollama show (#14285)

2026-02-16 13:03:34 -08:00

tokenizer

mlx: quantized embeddings, fast SwiGLU, and runtime fixes (#14884)

2026-03-17 11:21:38 -07:00

tools

add ability to disable cloud (#14221)

2026-02-12 15:47:00 -08:00