Change8

b9568

📦 llama-cppView on GitHub →
3 features🐛 2 fixes🔧 3 symbols

Summary

This release introduces MTP support for gemma-4 E2B and E4B assistants by updating model conversion logic and architecture support. It also provides numerous pre-compiled binaries across different operating systems and hardware configurations.

✨ New Features

  • Added support for gemma-4 E2B and E4B assistants via MTP.
  • Updated model converter to support smaller assistants.
  • Added masked_embd tensors to gemma4-assist architecture.

🐛 Bug Fixes

  • Removed temporary debug code related to gemma-4 conversion.
  • Filtered out masked_embedding tensors during gemma-4-mtp conversion.

Affected Symbols