b9802

ggml-org/llama.cppb9802Jun 25, 2026by github-actions[bot]1 days after b9789

What changed since b9789

low risk

b9802 ships no documented changes over b9789, so the delta appears to be routine build/CI housekeeping only.

Upgrade notes

The b9802 notes are empty, so no user-facing changes can be confirmed; treat this as a rebuild of the same source lineage as b9789. If you depend on the MoE-with-MTP quantization fix, it is already present in b9789 and carries forward. Verify against your own smoke tests before promoting, since the release notes provide no audit trail.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

Minor release with no specific changes documented in the release notes.

Release Notes (excerpt)

<details open> </details> **macOS/iOS:** - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) - iOS XCFramework **Linux:** - Ubuntu x64 (CPU) - Ubuntu arm64 (CPU) - Ubuntu s390x (CPU) - Ubuntu x64 (Vulkan) - Ubuntu arm64 (Vulkan) - Ubuntu x64 (ROCm 7.2) - Ubuntu x64 (OpenVINO) - Ubuntu x64 (SYCL FP32) - Ubuntu x64 (SYCL FP16) **Android:** - Android arm64 (CPU) **Windows:** - Windows x64 (CPU) - Windows arm64 (CPU)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories