b9748

ggml-org/llama.cppb9748Jun 21, 2026by github-actions[bot]same day as b9747

What changed since b9747

low risk

b9748 adds a 'verbose' field to the server schema, a small additive change over b9747's SSE progress endpoint.

New features

  • Server schema now exposes a 'verbose' field for controlling logging verbosity.

Upgrade notes

This is a minor, additive schema change; existing clients and configs should continue to work unchanged. If you use schema-driven tooling or generated API clients, regenerate them to pick up the new 'verbose' field. No migration or config edits are required.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

This release adds a 'verbose' field to the server schema to improve logging verbosity control. It includes standard pre-built binaries for various operating systems and hardware backends.

Key Highlights

  • Add 'verbose' field to server schema
  • Support for macOS, Linux, Android, Windows, and openEuler
  • Support for multiple hardware backends including CUDA, Vulkan, ROCm, and OpenVINO

Release Notes (excerpt)

<details open> server: add "verbose" field to schema (#24864) </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) **Android:** - Android arm64 (CPU) **Windows:**…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories