b9821

ggml-org/llama.cppb9821Jun 26, 2026by github-actions[bot]same day as b9820

What changed since b9820

low risk

b9821 adds --version, --licenses, and --help CLI flags on top of b9820's scheduler sync optimizations, with no other changes.

New features

  • New --version flag prints the build/version information from the command line.
  • New --licenses flag surfaces bundled third-party license texts.
  • New --help flag exposes usage information directly via the CLI.

Upgrade notes

This is a purely additive CLI change; existing flags, configs, and model files are unaffected, so a drop-in binary swap is sufficient. The scheduler synchronization and async CPU-to-CUDA copy work described in b9820 remains unchanged in this build. No migration or reconfiguration is required.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

Added command-line flags to display version, licenses, and help information.

Key Highlights

  • Added --version flag
  • Added --licenses flag
  • Added --help flag

Release Notes (excerpt)

<details open> app : allow --version, --licenses & --help (#25054) 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