Skip to content

Feat bump llamacpp#10

Merged
hsinatfootprintai merged 1 commit into
mainfrom
feat--bump-llamacpp
Apr 13, 2026
Merged

Feat bump llamacpp#10
hsinatfootprintai merged 1 commit into
mainfrom
feat--bump-llamacpp

Conversation

@hsinatfootprintai

Copy link
Copy Markdown
Contributor
  • Bump llama.cpp from b8606 to b8772, version v0.1.6 to v0.1.7
  • Expose KV cache type_k/type_v through Go bindings
  • Add android-arm64 CGO bindings and NDK cross-compilation (Dockerfile.android with build-test stage)
  • Refactor Makefile: build-libs-linux now builds all variants (cpu, cuda, vulkan) via shared define
  • Strip debug symbols from all .a builds (CMAKE_BUILD_TYPE=Release
    • strip --strip-debug) to keep files under GitHub's 100MB limit
  • Include prebuilt .a files for android-arm64

- Bump llama.cpp from b8606 to b8772, version v0.1.6 to v0.1.7
- Expose KV cache type_k/type_v through Go bindings
- Add android-arm64 CGO bindings and NDK cross-compilation
  (Dockerfile.android with build-test stage)
- Refactor Makefile: build-libs-linux now builds all variants
  (cpu, cuda, vulkan) via shared define
- Strip debug symbols from all .a builds (CMAKE_BUILD_TYPE=Release
  + strip --strip-debug) to keep files under GitHub's 100MB limit
- Include prebuilt .a files for android-arm64

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@hsinatfootprintai hsinatfootprintai merged commit 6b48f69 into main Apr 13, 2026
4 checks passed
@hsinatfootprintai hsinatfootprintai deleted the feat--bump-llamacpp branch April 13, 2026 11:05
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants