b10173

ggml-org/llama.cppb10173Jul 28, 2026by github-actions[bot]same day as b10172

What changed since b10172

low risk

Adds Laguna-S-2.1 model support; otherwise unchanged from b10172's WebGPU and buffer fixes.

New features

  • New LLM_TYPE enabling inference with Laguna-S-2.1 models.

Upgrade notes

This is a single-commit increment over b10172, so the WebGPU binding alias, >4GB buffer alignment, view offset, and recurrent-state-rollback fixes from the prior build are carried forward unchanged. No config or API migration is needed; simply rebuild or pull the new binaries if you need Laguna-S-2.1 support.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

Added support for the 'Laguna-S-2.1' Large Language Model type to the library.

Key Highlights

  • Added Laguna-S-2.1 LLM_TYPE

Release Notes (excerpt)

<details open> model: Add Laguna-S-2.1 LLM_TYPE (#26233) </details> **Website:** - <https://llama.app> **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)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories