b10146

ggml-org/llama.cppb10146Jul 27, 2026by github-actions[bot]same day as b10145

What changed since b10145

low risk

b10146 only adds a PowerPC-specific BF16 tiled GEMM optimization on top of b10145's --mlock behavior change.

New features

  • BF16 tiled GEMM optimization is now enabled on PowerPC CPUs, improving matrix multiplication throughput for BF16 models on that architecture.

Improvements

  • CPU backend gains architecture-specific BF16 GEMM tiling for PowerPC, with no impact on other platforms.

Upgrade notes

This is a single-commit increment over b10145; the --mlock semantics change (lock without mmap) landed in b10145 and is unchanged here. No config or CLI changes are required, and non-PowerPC users will see no behavioral difference.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

Enabled BF16 (Brain Float 16) tiled GEMM optimizations specifically for PowerPC architecture.

Key Highlights

  • BF16 tiled GEMM optimization for PowerPC

Release Notes (excerpt)

<details open> ggml-cpu: Enable BF16 tiled gemm optimization on PowerPC (#26068) </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)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories