release: prepare 0.39.0 - #948
Merged
Merged
Conversation
Bump VERSION_NAME 0.38.0 -> 0.39.0 and update all version-carrying docs: - CHANGELOG: consolidate [Unreleased] under [0.39.0] with a headline summary (includes the #947 AAR-publishing CI entry, now merged to develop). - README: BOM snippet -> 0.39.0, What's New in 0.39.0, Contributors (0.39.0). - docs/antora.yml: skainet_version attribute 0.38.0 -> 0.39.0 (used in the docs' dependency snippets). - kernel-support-matrix.adoc: regenerated via generateKernelMatrix — the Android column now shows native-jni for Q8_0/Q4_0/Q4_K/Q5_K/Q6_K (the new JNI backend), replacing panama-vector; version stamp -> 0.39.0. 0.39.0 headline: on-device AI on Android becomes real — the skainet-backend-jni-cpu JNI NEON backend (~24 tok/s SmolLM2-135M Q8_0 on a Pixel 8a vs ~3.8 scalar), plus Android streaming GGUF loads (#922), linkable K/N kernel klibs (#942), the Q4_0 NEON kernel (#939), GGUF loader fail-fast (#919), and a tensor-storage correctness pass (#927-#931). Local prep only — not pushed/tagged. Cut off develop after #947 merged, so the branch already carries the AAR-publishing workflow + pinned NDK.
|
📖 Documentation Preview The documentation has been built successfully for this PR. Generated Files:
Artifacts:
This comment will be updated automatically when the PR is updated. |
aharakal
approved these changes
Aug 11, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Release preparation for 0.39.0. Version bump + all version-carrying docs; no functional code changes.
Headline
On-device AI on Android becomes real. The
skainet-backend-jni-cpuJNI NEON backend brings the hand-tuned ARM matmul kernels to Android (where FFM can't run) — measured ~24 tok/s SmolLM2-135M Q8_0 decode on a Pixel 8a vs ~3.8 scalar (6.4x), clearing the on-device usability bar. Plus: Android streaming GGUF loads (no more full-file-heap OOM, #922), linkable Kotlin/Native kernel klibs (#942), a Q4_0 NEON kernel (#939), GGUF loader fail-fast (#919), and a tensor-storage correctness pass (#927–#931).What's in this branch
gradle.propertiesVERSION_NAME0.38.0 → 0.39.0 (single source of truth; BOM re-exports it)CHANGELOG.md[Unreleased]consolidated under[0.39.0]with a headline summary (incl. the #947 AAR-publishing CI entry)README.mddocs/antora.ymlskainet_versionattribute → 0.39.0 (used in docs dependency snippets)docs/…/kernel-support-matrix.adocgenerateKernelMatrix) — the Android column now showsnative-jnifor Q8_0/Q4_0/Q4_K/Q5_K/Q6_K, replacing panama-vectorNotes
developafter ci(publish): build & publish the skainet-backend-jni-cpu AAR on release (#946) #947 merged, so the branch already carries the AAR-publishing workflow (setup-androidstep) + the pinned NDK — it's genuinely tag-ready, not just changelog-ready.gradle propertiesresolvesversion: 0.39.0; no other0.38.0version refs remain outside CHANGELOG history.develop; retarget tomain/tag per the maintainers' release flow.