b10418

ggml-org/llama.cppb10418Aug 13, 2026by github-actions[bot]same day as b10417

What changed since b10417

low risk

SYCL backend gains host pinned memory support and fixes thread safety issues

New features

  • SYCL backend now supports host pinned memory for improved performance

Improvements

  • SYCL Host-to-Device memory access is improved via pinned memory support
  • Thread-safety issues in the SYCL backend are resolved

Bug fixes

  • Thread-safety issues in the SYCL backend are resolved

Upgrade notes

No configuration changes are required. Users utilizing the SYCL backend will benefit from improved memory access performance and a fixed thread safety issue.

Analyzed Oct 16, 2026

Upgrading?

Release notes summary

The SYCL backend gains support for host pinned memory to improve Host-to-Device memory access, accompanied by a thread-safety fix.

Key Highlights

  • SYCL backend: Support for host pinned memory
  • Fix thread-safety issues in the SYCL backend
  • Comprehensive builds for all supported platforms

Release Notes (excerpt)

<details open> [SYCL] Support host pinned mem to improve SYCL Host-to-Device Memory Access (#26789) * support host pinned mem, ggml_backend_sycl_host_buffer_type_get_max_size, * fix the thread-safe issue </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)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories