# llama.cpp release b11468 adds cpp‑httplib 0.60.0 and new binaries

> The open‑source LLaMA inference library updates its HTTP library and ships fresh builds for macOS, iOS, Linux and GPU back‑ends.

Oossa · 2026-10-07 · https://oossa.com/en/llama-cpp-release-b11468-adds-cpp-httplib-0-60-0-and-new-binaries

The ggml‑org team released llama.cpp version b11468. The update upgrades the bundled cpp‑httplib library to version 0.60.0. It also provides pre‑built binaries for macOS Apple Silicon, macOS Intel, iOS, and several Ubuntu flavors, including CPU, Vulkan and CUDA 12.8 builds.

## The facts

- Release version b11468 published on 2026‑10‑07
- Adds cpp‑httplib 0.60.0 and new Ubuntu CUDA 12.8 binary

## Why it matters

Developers can now download ready‑to‑run LLaMA binaries for more platforms, saving time on compilation.

## Sources & references

1. [ggml-org/llama.cpp b11468](https://github.com/ggml-org/llama.cpp/releases/tag/b11468) – llama.cpp, 2026-10-07

Last updated: 2026-10-07