feat(native): prepare llama.cpp v0.4.0 adoption - #478
Merged
Conversation
Contributor
|
Chat app preview removed for |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adopt matching native and Web llama.cpp v0.4.0 runtimes, with regenerated native bindings, MTMD ABI updates, session migration tests, and Apple companion 0.0.18 preparation.
Closes #479 (pre-existing Markdown writer-audit contamination by installed website dependencies; narrowly fixed as a validation prerequisite).
Production-readiness scope
78be0c8c628cd8cbc6a1268b1a9758c3d6d052a6; source89178be67c3c84300bc1b129182bd5bc5a8e21fc; upstreamv0.4.0@5266f24da75dc449bd56cbed7addb9c8e4a6a73e.111eefc3588842cebfe665b363378edca34924764610263e1eda5280dfcfaa27; native manifest SHA-2566187e6483eb03c86d79bb774e01ece71b201cb00561550bbc948b20d237b5cdc.Publication prerequisite completed with user authorization
The failed automatic Web scan 34104915793 was retried, completed successfully, and dispatched publication 34117166273. That publication completed SUCCESS and produced immutable v0.1.43 using already-successful candidate 34100775215 and qualification 34102054173. The previous failure was a GitHub API timeout before credential exposure. No safeguards were bypassed or environment settings changed.
Validation
check_webgpu_bridge_tag.dart --verify-manifest: PASS, including 17 consumer pins, v0.4.0 family parity, exact provenance and manifest bytes.chat-app-web-real-model-smoke: PASS on local Chromium CPU/WASM worker with stories15M, pinned v0.1.43 staged in the deployable build; model load and nonempty generation, no page errors/request failures.2eed00e8; pipeline evidence, not a speedup claim.High-risk regression review
451518d20590b9f75e95d7957649e856a082f802; base3ad853d286689046dec659938cdbb082b97ce00b.native_v040_independent_qa: PASS on exact final head. Prior package-pairing finding corrected with explicit unreleased warning, safe published pairing, and mandatory same-checkout overrides. No remaining blocker in the independent bounded review; final hosted CI still required.