b10054

ggml-org/llama.cppb10054Jul 17, 2026by github-actions[bot]same day as b10052

What changed since b10052

low risk

Delta between b10052 and b10054 is a docs-only note on OpenCL with Adreno 810 plus routine binary builds.

Improvements

  • Added documentation guidance for using the OpenCL backend on Adreno 810 hardware.
  • Refreshed prebuilt binaries for macOS, iOS, Linux, Windows, and Android at the new build tag.

Upgrade notes

This is effectively a documentation and packaging bump, so no code or config migration is required. Users on Adreno 810 devices should consult the new OpenCL note before enabling that backend. The Hexagon L2 cache rework landed in the prior release, so validate that behavior if you skipped b10052.

Analyzed Oct 31, 2026

Upgrading?

Release notes summary

Adds documentation notes regarding OpenCL usage with specific Adreno 810 hardware and includes standard release binaries.

Key Highlights

  • Added documentation for OpenCL usage with Adreno 810.
  • Cross-platform binaries included for macOS, Linux, Windows, and Android.

Release Notes (excerpt)

<details open> docs: added a note about using OpenCl with Adreno 810 (#25786) </details> **Website:** - <https://llama.app> **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:**…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories