The llama.cpp project has released version b12237, which includes support for Gemma 4's input audio stream. This update addresses an issue where real-time embeddings were incorrectly forced on for audio generation, causing chat models with audio streams to abort. The fix ensures that embeddings are only enabled when necessary for audio generation. AI
IMPACT Improves audio streaming capabilities for models like Gemma 4 within the llama.cpp framework.
RANK_REASON This is a software update for a specific tool, not a frontier model release.
Read on llama.cpp — Releases →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →