chore: bump llama.cpp to b10450; 1.0.10438:0 → 1.0.10450:0 - #23
Closed
helix-nine wants to merge 1 commit into
Closed
chore: bump llama.cpp to b10450; 1.0.10438:0 → 1.0.10450:0#23helix-nine wants to merge 1 commit into
helix-nine wants to merge 1 commit into
Conversation
Member
|
Superseded by #22, which now carries this bump. #22 (Set Model prefill) and this one both rewrote
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Bumps llama.cpp from build
b10438tob10450— 12 upstream commits. StartOS version1.0.10438:0→1.0.10450:0.All four image variants were confirmed published on GHCR before pinning (
server-,server-cuda-,server-rocm-,server-vulkan-atb10450), with the expected arches (rocm x86-only, the rest amd64+arm64).Upstream highlights
server: theyield_to_queuethread model was re-designed, improving behaviour under concurrent requests.structuredContentwhencontentis empty.--models-dircan load MTP assistant models.cpp-httplib→ 0.53.1 and BoringSSL → 0.20260813.0.Full commit range: ggml-org/llama.cpp@b10438...b10450
Deprecation checked, no package change needed
Upstream deprecated
--mmap/--no-mmap/--mlock/--direct-ioin favour of-lm/--load-mode(#26934). They still parse and only emit a warning, so nothing breaks. This package builds its serve args from-hf,-hff,-c,-ngl,--hostand--portonly, so none of the deprecated flags are used bymain.tsor the presets; the release notes mention it for users who pass them via Set Model's extra arguments.The presets in
startos/actions/presets.tswere reviewed against the range — no flag renames or server-API changes affect them.Other
@start9labs/start-sdkis already at the latest published version (2.0.9) — no SDK bump.*-startosgit dependencies, so no dependency refresh.Test plan
npm run check(tsc) — green.1.0.10380:0, so1.0.10450:0is free.make generic/ full build verification left to review, per the monitor-cycle policy.