# llama.cpp b11782 release fixes token count bug

> The open‑source LLM runner updates its server code to correctly count completion tokens when generating multiple outputs and adds new binaries for macOS, iOS and Linux.

Oossa · 2026-10-21 · https://oossa.com/en/llama-cpp-b11782-release-fixes-token-count-bug

ggml‑org released llama.cpp version b11782 on 21 Oct 2026. The update patches a server issue that under‑counted usage.completion_tokens when n > 1, meaning token usage stats were low for batch generations. The release also provides fresh pre‑built binaries for Apple Silicon, Intel Macs, iOS, and several Ubuntu builds (CPU, Vulkan, CUDA).

## The facts

- Fix: correct usage.completion_tokens count for n > 1 (#29486).
- New binaries for macOS ARM64, macOS Intel, iOS XCFramework, Ubuntu x64/arm64 (CPU, Vulkan, CUDA).

## Why it matters

Developers will see accurate token usage, helping them monitor costs and performance when running multiple completions.

## Sources & references

1. [ggml-org/llama.cpp b11782](https://github.com/ggml-org/llama.cpp/releases/tag/b11782) – llama.cpp, 2026-10-21

Last updated: 2026-10-21