b10211

ggml-org/llama.cppb10211Jul 31, 2026by github-actions[bot]same day as b10210

What changed since b10210

low risk

b10211 is a housekeeping release that only bumps the Vulkan SDK to 1.4.357.0, with no other changes over b10210.

Improvements

  • Vulkan SDK updated to 1.4.357.0, bringing the build in line with the latest Vulkan headers and driver capabilities.
  • Vulkan backend binaries are rebuilt against the newer SDK, which may improve compatibility with recent GPU drivers.

Upgrade notes

This is a narrow build-tooling bump, so no config or API changes are needed. Only Vulkan-backend users gain anything; CPU, ROCm, and Metal users can treat b10211 as functionally identical to b10210. The server token-replay fix from b10210 remains included.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

This release updates the Vulkan SDK to version 1.4.357.0 to ensure compatibility with the latest hardware and driver features.

Key Highlights

  • Updates Vulkan SDK to version 1.4.357.0

New Features

  • Vulkan SDK update

Release Notes (excerpt)

<details open> vulkan: update vulkan sdk to 1.4.357.0 (#26303) </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) **Android:**…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories