b9750

ggml-org/llama.cppb9750Jun 21, 2026by github-actions[bot]same day as b9748

What changed since b9748

medium risk

b9750 adds Jinja `call` statement support to the chat template engine, with internal refactoring of the function handler.

New features

  • Jinja templates can now use the `call` statement, enabling reusable macro-style blocks in chat templates.

Improvements

  • Template rendering code was de-lambda'd and simplified for easier maintenance.
  • Caller context is now tracked inside the function handler rather than externally.

Upgrade notes

No configuration or API changes are required; the new Jinja capability is additive and only affects templates that use `call` blocks. Templates relying on the previous lack of `call` support may now render differently, so re-test custom chat templates after upgrading.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

This release implements a new 'call statement' feature for Jinja templates, simplifying the implementation and reorganizing the caller context inside the function handler. It provides pre-built binaries for macOS, Linux, Android, Windows, and openEuler.

Key Highlights

  • Implement Jinja call statement functionality
  • Simplify implementation and de-lambda code
  • Move caller context inside function handler
  • Comprehensive binary support for multiple platforms and architectures

Release Notes (excerpt)

<details open> jinja : implement call statement (#24847) * implement call statement * undo unintended change * de-lambda * simplify * move caller context inside function handler </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)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories