Topic: release

Hermes Agent v0.19.1 (v2026.7.30) was released on July 30, 2026, consolidating over a thousand merged pull requests into a stable version for use by downstream consumers. This release is crucial for ensuring compatibility and stability in Docker images, hosted deployments, and fresh installations.

The ggml/llama.cpp project added support for alternative convolution layouts, enhancing flexibility and ensuring compatibility across different computational kernels. This update is crucial for improving the library's versatility in handling various neural network architectures.

The ggml-cuda project updated its code to disable Multi-Memory Queue (MMQ) on devices with less than 48 KiB of shared memory, ensuring optimal performance across different hardware configurations. This update is crucial for maintaining compatibility and efficiency in various computational environments.