b10308

ggml-org/llama.cppb10308Aug 7, 2026by github-actions[bot]same day as b10307

What changed since b10307

low risk

b10308 is a single-fix follow-up that mitigates a crash on Windows MSYS2 UCRT64 builds using GCC 16.1.0.

Improvements

  • Improved stability of Windows MSYS2 UCRT64 builds compiled with GCC 16.1.0.

Bug fixes

  • Mitigated a crashing issue observed in the Windows MSYS2 UCRT64 environment with GCC 16.1.0 (#26555).

Upgrade notes

This is a narrow patch on top of b10307; the SYCL NVFP4/UE4M3 scale-parsing fix from the previous build is already included. Only users building or running on Windows MSYS2 UCRT64 with GCC 16.1.0 need to act, and no config or model changes are required.

Analyzed Oct 30, 2026

Upgrading?

Release notes summary

A bug fix release addressing a crashing issue on Windows MSYS2 UCRT64 environments running GCC 16.1.0.

Key Highlights

  • Mitigated crashing issue on Windows MSYS2 UCRT64 (GCC 16.1.0) (#26555)

Release Notes (excerpt)

<details open> Mitigate crashing issue on Windows MSYS2 UCRT64 environment (GCC 16.1.0) (#26555) </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)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories