chore: bump upstream llama.cpp manifest to b10063#9
Draft
cashcon57 wants to merge 1 commit into
Draft
Conversation
b9937 predates the mainline ternary Q2_0 Metal kernels (ggml-org/llama.cpp#25419, first shipped in b9994; CPU kernels in #24448). b10063 lets the upstream backend load ternary models such as Ternary-Bonsai in the mainline Q2_0_g64 format on macOS and CPU. Verified on an M3 Max with the b10063 macos-arm64 release binaries and Ternary-Bonsai-8B-Q2_0_g64 (Metal init, clean load, coherent generation), and confirmed all eight asset names listed here exist verbatim on the b10063 release. Companion to the app-side pin bump: AtomicBot-ai/Atomic-Chat#187.
cashcon57
marked this pull request as draft
July 17, 2026 17:03
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Bumps
backends/manifest.jsonfromb9937tob10063so the upstream backend gains the mainline ternaryQ2_0kernels (CPU: ggml-org/llama.cpp#24448, Metal: ggml-org/llama.cpp#25419, first shipped inb9994). This enables ternary models such as Ternary-Bonsai (Q2_0_g64files) on macOS and CPU; Vulkan/CUDA ternary are still in review upstream, so those platforms are unaffected either way.Verified on an M3 Max with the
b10063macos-arm64release binaries andprism-ml/Ternary-Bonsai-8B-ggufQ2_0_g64: Metal initializes, the model loads (254q2_0tensors, file typeQ2_0), and generation is coherent. All eight asset filenames in this manifest exist verbatim on theb10063release.Note: this manifest goes live for all installs on merge, so you may prefer to land the app-side pin first — especially since AtomicBot-ai/Atomic-Chat#187 also fixes the extension building
.zipURLs for macOS backends (ggml-org ships.tar.gz), without which macOS clients 404 on this runtime download and silently keep their current backend: AtomicBot-ai/Atomic-Chat#187 (same bump forPINNED_BACKEND_TAG, the offline fallback manifest, andLLAMACPP_UPSTREAM_TAG).