b9785

ggml-org/llama.cppb9785Jun 25, 2026by github-actions[bot]same day as b9784

What changed since b9784

low risk

Adds chat mode security hardening and Hexagon backend performance improvements.

New features

  • Chat mode caps check hardening

Improvements

  • Improved caps validation in chat mode

Upgrade notes

Chat mode input handling now enforces stricter caps validation; ensure inputs comply to avoid rejection.

Analyzed Oct 18, 2026

Upgrading?

Release notes summary

Hardens the chat mode input handling to improve security by enforcing stricter checks on input caps.

Key Highlights

  • Chat mode security hardening
  • Improved caps validation

Release Notes (excerpt)

<details open> chat: harden caps check (#24973) </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:** - Windows x64 (CPU)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories