b9882

ggml-org/llama.cppb9882Jul 6, 2026by github-actions[bot]same day as b9881

What changed since b9881

low risk

Build scripts now authenticate UI asset downloads with HF_TOKEN; no runtime or API changes.

Improvements

  • Build scripts now pass HF_TOKEN when fetching UI assets, enabling authenticated downloads of private or restricted resources.
  • UI asset download step in the build pipeline is more reliable for environments requiring Hugging Face authentication.

Bug fixes

  • Fixed UI asset downloads that previously failed when the assets were gated behind Hugging Face authentication.

Upgrade notes

This release only touches build/packaging scripts, so runtime behavior is unchanged from b9881. If you build from source and fetch UI assets from a private or gated Hugging Face repo, export HF_TOKEN in your build environment. No config or model migration is required.

Analyzed Oct 31, 2026

Upgrading?

Release notes summary

The build scripts have been updated to utilize the Hugging Face (HF) token when downloading UI assets, ensuring authenticated access to private or restricted resources.

Key Highlights

  • Update build scripts to use HF_TOKEN
  • Fix UI asset downloads

Release Notes (excerpt)

<details open> scripts : use HF_TOKEN when downloading UI assets (#25280) Signed-off-by: Adrien Gallouët <angt@huggingface.co> </details> **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