b9637

ggml-org/llama.cppb9637Jun 14, 2026by github-actions[bot]same day as b9632

What changed since b9632

low risk

Adds a dedicated Cohere2-MoE (North Code) chat parser on top of the prior Jinja filter alias additions.

New features

  • Dedicated chat parser for the Cohere2-MoE (North Code) model format, improving chat interaction handling for that model family.

Improvements

  • Internal naming cleanups in the new chat parser following review feedback.
  • Refreshed prebuilt binaries for all supported platforms.

Upgrade notes

No config or migration steps are required; existing Jinja template behavior from b9632 is unchanged. Users running Cohere2-MoE / North Code models should pick up this build to get correct chat formatting. Binaries are rebuilt per platform, so re-download rather than reuse older artifacts.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

Added a dedicated chat parser for the Cohere2-MoE (North Code) model format to improve chat interaction handling.

Key Highlights

  • Added dedicated Cohere2MoE (North Code) chat parser
  • Updated binaries for all platforms

Release Notes (excerpt)

<details open> chat: add dedicated Cohere2MoE (North Code) parser (#24615) * chat: add dedicated Cohere2MoE (North Code) parser * Some renames to make @CISC happy :> </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)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories