fix: repair regressed mlx-swift submodule pin, wire up Gemma4MTPBench - #163
Merged
Conversation
…x-swift submodule pins mlx-swift-lm was uncommitted-pinned backward past the commit that introduced DualModelMTP/MTPTokenIterator/Gemma4AssistantModel, breaking Gemma4MTPBench and forcing MTP speculative decoding to be commented out in InferenceEngine.swift as a workaround. Repointing both submodules to their current origin/main tips (mlx-swift-lm past the merged DSA stage-2 PR #61, mlx-swift past the matching MLXFast.fromFp8 addition) restores those types and lets the benchmark build again — no source workaround needed. Also adds scripts/bootstrap_local_tests.sh, which mirrors CI's "Install MLX Metal library" step (pip install mlx, copy its bundled metallib into every built .xctest bundle) so `swift test` is runnable locally without the manual cmake+make dance. Addresses the Tier 3 item in #128. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
mlx-swiftsubmodule pin forward to its currentorigin/maintip (5639a6d). The previously pinned commit was actually an ancestor of the prior pin — a regression, not a bump — that was missingMLXFast.fromFp8, whichmlx-swift-lm'sFP8Linear.swiftnow depends on.Sources/Gemma4MTPBenchbenchmark intoPackage.swiftas anexecutableTarget. It depends onDualModelMTP/MTPTokenIterator/Gemma4AssistantModel, which only exist oncemlx-swift-lmis past the DSA stage-2 merge (already the pin onmain) — so it silently never built before.scripts/bootstrap_local_tests.sh, which mirrors CI's "Install MLX Metal library" step (pip installmlx, copy its bundledmlx.metallibinto every built.xctestbundle) soswift testis runnable locally without CI's help. This is the Tier 3 item from Test coverage plan: the unit suite has never caught a bug #128.Test plan
swift build --build-tests— clean build, 0 errors, in an isolated worktree againstorigin/main./scripts/bootstrap_local_tests.shthenswift test --skip-build --filter SwiftLMTests— 161 tests, 0 failuresswift test --skip-build --filter SwiftBuddyTests --disable-swift-testing— 86 tests (9 skipped), 0 failures🤖 Generated with Claude Code