b9608

ggml-org/llama.cppb9608Jun 12, 2026by github-actions[bot]same day as b9606

What changed since b9606

low risk

b9608 is a housekeeping release that only bumps the vendored cpp-httplib library to 0.47.0, with no core logic changes.

Improvements

  • Vendored cpp-httplib updated to 0.47.0, picking up upstream fixes and hardening in the HTTP server layer.

Upgrade notes

This is a drop-in vendor bump with no API, config, or model-format changes; no migration steps are required. The EAGLE3 speculative decoding work landed in the prior release (b9606), so teams upgrading from b9606 gain nothing functionally here. Rebuild binaries if you rely on the bundled HTTP server, since the change is compile-time only.

Analyzed Oct 31, 2026

Upgrading?

Release notes summary

Updates the embedded cpp-httplib library to version 0.47.0. This is a vendor update with no functional changes to the core library logic.

Key Highlights

  • Update cpp-httplib to 0.47.0

New Features

  • Vendor update (cpp-httplib 0.47.0)

Release Notes (excerpt)

<details open> vendor : update cpp-httplib to 0.47.0 (#24395) 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) DISABLED **Android:**…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories