CERBERUS/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-10-20 18:41:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

mlx, mlxrunner: move the MLX engine out of x/

Browse source 
The MLX runner is the only Go inference runner left and is no longer
experimental, so its packages leave x/. The bindings become a top-level
mlx package beside the carried patches in mlx/compat, mirroring how
llama/ holds the llama.cpp integration, and the runner becomes mlxrunner
with the architectures nested under the package they implement.
Subpackages move with their parent unless listed.

  x/mlxrunner/mlx            mlx
  x/internal/mlxthread       mlx/mlxthread
  x/internal/mlxthreadtest   mlx/mlxthread/mlxthreadtest
  x/internal/mlxtest         mlx/mlxtest
  x/quant                    mlx/quant
  mlx/compat/*.patch         mlx/compat/mlx-c   (MLX patches go in mlx/compat/mlx)
  x/mlxrunner                mlxrunner
  x/models/nn                mlxrunner/nn
  x/models/<arch>            mlxrunner/model/<arch>
  x/mlxrunner/imports.go     mlxrunner/model/architectures   (new package)
  x/create                   create
  x/safetensors              fs/safetensors
  x/tokenizer                mlxrunner/tokenizer

Every package keeps its name, so the Go changes are the import path
rewrites the moves force, and the CMake, Dockerfile, CI cache keys, drift
check and Darwin payload script follow the new paths. Four edits are not
paths: the runner's blank architecture imports become the package
mlxrunner/model/architectures, so the list to extend for a new model sits
beside the architecture directories; a depguard rule keeps the two test
harnesses out of non-test code, as the x/internal placement used to; the
CI change filter's two entries for the long-deleted x/imagegen/mlx now
name the bindings' CMake project and the carried patches, so a change to
either builds the payload; and the tokenizer parity test reads its
fixtures from its own testdata instead of walking out of x/.

x/server and x/imagegen/manifest stay for the next two commits.
This commit is contained in:
Jesse Gross 2026-09-15 19:11:36 -07:00
parent bef41f710a
commit 2e036e7cdf
283 changed files with 460 additions and 456 deletions
Download patch file Download diff file Expand all files Collapse all files

6
.github/scripts/prepare_mlx_darwin.sh vendored
View file

@ -9,7 +9,7 @@
#
# The payload also depends on Ollama's payload build rules (cmake glue and
# carried mlx/compat patches) and the xgrammar native wrapper
# (x/mlxrunner/xgrammar/native). Rule drift rebuilds the whole payload from
# (mlxrunner/xgrammar/native). Rule drift rebuilds the whole payload from
# source; wrapper-only drift rebuilds just libollama_xgrammar.dylib.
#
# If no release matches the MLX pins (e.g. right after a pin bump), the
@ -54,7 +54,7 @@ read_pin() {
# Native wrapper sources compiled into libollama_xgrammar.dylib — keep in
# sync with the ollama_xgrammar target in cmake/mlx/CMakeLists.txt.
xgrammar_native_dir=x/mlxrunner/xgrammar/native
xgrammar_native_dir=mlxrunner/xgrammar/native
# Payload build rules beyond the MLX_VERSION/MLX_C_VERSION pins.
payload_rule_files=(
@ -62,7 +62,7 @@ payload_rule_files=(
"cmake/apply-git-patches.cmake"
"cmake/mlx/CMakeLists.txt"
"cmake/mlx/CMakePresets.json"
"x/mlxrunner/mlx/CMakeLists.txt"
"mlx/CMakeLists.txt"
)
# Build-rule inputs: the rule files plus carried MLX/MLX-C patch content.