Commit graph

5 commits

Author SHA1 Message Date
Daniel Hiltgen
b9cd4b1efb
xgrammar: add standalone CMake project for native library (#18611)
Move the ollama_xgrammar target into mlxrunner/xgrammar/native so it
can be configured on its own against an installed xgrammar. cmake/mlx
now adds it as a subdirectory and still uses the pinned xgrammar.
2026-09-23 11:20:59 -07:00
Jesse Gross
2e036e7cdf mlx, mlxrunner: move the MLX engine out of x/
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.
2026-09-16 14:06:08 -07:00
Daniel Hiltgen
d3efc63263
ci: bound and cache the macOS MLX payload build (#18240)
Avoid unbounded parallel builds on small runners, and cache the payloads for repeated runs.
2026-09-04 14:38:05 -07:00
Daniel Hiltgen
59fe23d85c
ci: rebuild MLX macOS test payloads the release can't supply (#18219)
* ci: rebuild MLX macOS test payloads the release can't supply

The MLX unit test dependency payload can go stale when a PR changes the
xgrammar wrapper (release dylib lacks the new symbols) or bumps MLX pins (no
matching release, so MLX tests silently skipped). Compare the matched tag's
build rules and wrapper sources against the checkout, rebuilding only
libollama_xgrammar.dylib on drift; with no matching release, build one Metal
variant at the platform default.

* address comments
2026-09-03 14:17:21 -07:00
Daniel Hiltgen
e5e4377115
ci: wire up MLX unit tests for PR runs (#17022)
* ci: wire up MLX unit tests for PR runs

Download the latest Darwin release payload matching the current MLX and MLX-C revisions so macOS PR tests can exercise MLX without rebuilding it. If no matching release exists after a pin bump, leave MLX tests skipped until the next release.

Add whole-tree race coverage and smoke-run committed benchmarks. Verify generated UI types, and stabilize tests exposed by the broader CI coverage.

* review comments

* mlx: run tests on one pinned worker

Keep MLX tests and benchmarks on a shared pinned thread while preserving Fatal, Skip, and Cleanup semantics. Also clean stale CI payloads and ensure updater workers shut down cleanly.

* addres comments
2026-09-01 16:59:36 -07:00