b10149

ggml-org/llama.cppb10149Jul 27, 2026by github-actions[bot]same day as b10148

What changed since b10148

low risk

Only change between b10148 and b10149 is a test-only removal of a redundant sync in test-save-load-state.

Improvements

  • Removed an unnecessary synchronization call from the test-save-load-state test, trimming test runtime.

Upgrade notes

No runtime, CLI, or API changes are involved; this build differs from b10148 only in test code. Upgrading is a drop-in replacement with no config or migration steps.

Analyzed Oct 31, 2026

Upgrading?

Release notes summary

Removed an unnecessary synchronization call in the state save/load test to improve performance.

Key Highlights

  • Removed unnecessary sync in test-save-load-state

Release Notes (excerpt)

<details open> tests : remove unnecessary sync in test-save-load-state (#26166) </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