b9976

ggml-org/llama.cppb9976Jul 12, 2026by github-actions[bot]same day as b9975

What changed since b9975

low risk

b9976 only corrects the conditional that surfaces the unsupported tensor-split-mode error message; no functional logic changes.

Improvements

  • Users on architectures lacking tensor split mode support now reliably see the 'LLAMA_SPLIT_MODE_TENSOR not implemented' message instead of silence or a misleading error.

Bug fixes

  • Fixed the conditional guarding the unsupported tensor split mode error so it triggers under the correct conditions.

Upgrade notes

This is a single-commit follow-up to b9975 with no API, config, or model-format changes; binaries can be swapped in place. Only behavior difference is clearer diagnostics when requesting tensor split mode on unsupported architectures.

Analyzed Oct 24, 2026

Upgrading?

Release notes summary

Fixes the conditional logic for displaying an error message regarding unsupported tensor split modes on specific architectures, ensuring users receive appropriate feedback.

Key Highlights

  • Error message display fix
  • Tensor split mode support validation
  • No functional logic changes

New Features

  • UI/UX improvement for error messages

Release Notes (excerpt)

<details open> Fix conditional to display 'LLAMA_SPLIT_MODE_TENSOR not implemented for architecture' message (#24926) </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)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories