b9341: convert : support Gemma4ForCausalLM architecture (#23682)
The llama.cpp project has released version b9341, which includes support for the Gemma4ForCausalLM architecture. This update allows for greater compatibility and integration with Google's Gemma models within the llama.cpp framework. The release also contains a fix for indentation issues. AI
IMPACT Enhances compatibility for running Google's Gemma models on local hardware via llama.cpp.