Change8

b9585

📦 llama-cppView on GitHub →
🐛 1 fixes🔧 1 symbols

Summary

This release fixes an issue in granite speech model inference by correctly applying the embedding scale when deepstack is disabled. It also includes minor cleanup in tests.

🐛 Bug Fixes

  • Fixed granite speech model inference by applying embedding scale when deepstack is not used.

Affected Symbols