Scam.ai has announced a partnership with Qualcomm to launch Halo, an on-device deepfake detection model for live video calls. Unveiled at Computex 2026, Halo operates locally on Qualcomm-powered devices, providing real-time detection of synthetic videos without relying on cloud infrastructure. This development aims to tackle the rising threat of deepfake fraud, especially in sensitive areas like HR interviews and executive communications. The partnership enhances Scam.ai's ability to offer secure and private video call solutions, marking a significant advancement in deepfake detection technology.
Read originalThe latest b9946 release of llama.cpp focuses on optimizing Hexagon operations, particularly unary operations, to improve performance and efficiency. By introducing tiling for wide rows and replacing divisions with fastdiv, the update aims to prevent VTCM overflow and streamline code execution. The release also includes tracing instrumentation and specialized thread functions to enhance code generation. While no new models are introduced, these technical improvements make llama.cpp more robust and efficient for developers working with Hexagon architectures.
The latest b9948 release of llama.cpp focuses on optimizing memory usage in CUDA operations, specifically in the ggml_top_k() and ggml_argsort() functions. By processing data in smaller chunks, the update reduces the need for large temporary buffers, enhancing performance on CUDA-enabled systems. This release also includes minor code improvements like allocating temporary destinations only once and refining the use of ternary operators. While no new model architectures are introduced, these changes make llama.cpp more efficient for developers working with CUDA, particularly in memory-constrained environments.
The latest b9951 release of llama.cpp marks a significant enhancement in the ET backend, introducing a range of new kernels and performance optimizations. This update includes the addition of various matrix operations and support for FlashAttention, which promises to improve computational efficiency. The release also focuses on vectorization and parallelization, aiming to boost performance across different operations. These changes make the ET backend more robust and capable, potentially benefiting developers working with complex AI models by offering improved speed and functionality.