jmorganca 582d93ab22 fix: lazy init MLX for quantization and improve library discovery ...

- Add lazy MLX initialization in quantizeTensor to ensure the library
  is loaded when quantization is requested
- Add exe-relative build path search for dev mode on macOS, so the
  ollama binary can find libmlxc.dylib in build/lib/ollama/ when
  running from the repo root

2026-01-17 22:46:20 -08:00

..

agent

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

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

cmd

cmd: enable multi-line input and shift enter (#13694)

2026-01-14 17:52:46 -08:00

create

fix: lazy init MLX for quantization and improve library discovery

2026-01-17 22:46:20 -08:00

imagegen

Add experimental image generation fields to /api/generate (#13753)

2026-01-17 18:27:41 -08:00

kvcache

Add experimental MLX backend and engine with imagegen support (#13648)

2026-01-08 16:18:59 -08:00

ml

MLX - dynamic loading of mlx-c (#13735)

2026-01-16 16:34:22 -08:00

model

Add experimental MLX backend and engine with imagegen support (#13648)

2026-01-08 16:18:59 -08:00

server

Fix create and show commands for experimental models (#13741)

2026-01-16 14:31:55 -08:00

tools

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

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