b9981

ggml-org/llama.cppb9981Jul 13, 2026by github-actions[bot]same day as b9980

What changed since b9980

low risk

b9981 only bumps the vendored cpp-httplib HTTP server library to 0.50.1, with no functional changes to llama.cpp itself.

Improvements

  • Vendored cpp-httplib dependency updated to version 0.50.1, pulling in upstream fixes and refinements to the embedded HTTP server.
  • Server-side HTTP handling benefits from the newer library release without any code changes on llama.cpp's side.

Upgrade notes

This is a pure dependency refresh; no configuration, CLI flags, or API surfaces change, so a drop-in replacement of the binaries is sufficient. Rebuild from source if you vendor cpp-httplib yourself to stay in sync with upstream 0.50.1. The /v1/models modality reporting fix from b9980 remains in effect.

Analyzed Oct 24, 2026

Upgrading?

Release notes summary

Updates the embedded HTTP server library (cpp-httplib) to version 0.50.1, incorporating the latest fixes and improvements from the dependency.

Key Highlights

  • cpp-httplib vendor update
  • HTTP server library upgrade
  • Version 0.50.1 release

New Features

  • Dependency update
  • HTTP server library maintenance

Release Notes (excerpt)

<details open> vendor : update cpp-httplib to 0.50.1 (#25576) </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