Models & Labs
llama.cpp adds support for Gemma4ForCausalLM
llama.cpp Releaseshigh confidence
Why it matters
- →Expands llama.cpp's support to include Gemma4ForCausalLM, broadening its utility for developers.
- →Enhances performance and flexibility in AI applications using the Gemma4 architecture.
- →Addresses technical issues, improving the tool's usability and integration.
llama.cpp has released an update that includes support for the Gemma4ForCausalLM architecture. This development allows users to utilize the Gemma4 architecture for causal language modeling, broadening the tool's applicability. The update also addresses indentation issues, improving the overall user experience. This enhancement is part of llama.cpp's ongoing efforts to expand its support for various AI models.
Read originalMore from llama.cpp Releases
Models & Labsmodels
Llama.cpp b9329 Release Enhances CUDA Performance
The b9329 release of llama.cpp brings a notable performance enhancement with the integration of a fast Walsh-Hadamard transform for CUDA, which is set to improve computational efficiency. This update also includes optimizations such as unrolling and changes from size_t to int, aimed at boosting processing speed. The release is compatible with platforms like macOS, Linux, Windows, and openEuler, ensuring developers can leverage these improvements across different environments. While there are no new models introduced, the emphasis on performance optimization makes this update significant for those working with CUDA and other supported systems.
llama.cpp Releases
Models & Labsmodels
llama.cpp b9330 release improves model performance
The b9330 release of llama.cpp resolves a key issue by correctly tagging the ffn_latent operation as MUL_MAT, aligning it with the backend's operational expectations. This correction ensures that weights and their matrix multiplications remain on the GPU, avoiding unnecessary CPU fallback and graph splitting. As a result, performance on the Nemotron 3 Super 120B Q5_K_M model has significantly improved, with throughput increasing from 64.9 to 103.22 tokens per second. This update reflects llama.cpp's dedication to enhancing AI model performance across different computing environments, including macOS with KleidiAI and Ubuntu with ROCm 7.2. By maintaining efficient GPU processing, llama.cpp continues to optimize AI model execution, ensuring robust performance on platforms like CUDA 12 and CUDA 13.
