b10358

ggml-org/llama.cppb10358Aug 11, 2026by github-actions[bot]same day as b10357

What changed since b10357

low risk

b10358 is a maintenance-only follow-up that addresses review comments from PR 25532, with no functional changes over b10357.

Improvements

  • Code cleanup and refinement in response to reviewer feedback on PR 25532.
  • Minor code-quality and correctness touch-ups with no behavioral impact expected.

Bug fixes

  • Addressed review-comment issues from PR 25532, which may correct small edge-case defects.

Upgrade notes

This is a housekeeping build with no API, config, or model-format changes, so upgrading from b10357 should be a drop-in binary swap. No migration steps are required; the OpenCL Flash Attention prefill optimization from b10357 carries over unchanged.

Analyzed Oct 29, 2026

Upgrading?

Release notes summary

Code maintenance release addressing specific review comments from a previous pull request to ensure code quality and correctness.

Key Highlights

  • Addressed review comments for PR 25532
  • Code cleanup and refinement

New Features

  • Bug fix and code quality improvement

Release Notes (excerpt)

<details open> Address review comment of PR 25532 (#26852) </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 7.14) - 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