ggml/llama.cpp releases: b11945

TL;DR

The ggml/llama.cpp project has updated to include new models LiquidAI/d1-2B and LiquidAI/d1-omni-2B, expanding its model offerings. These updates are significant as they enhance the project's capabilities in handling speech tasks and provide more options for users interested in these specific models.

Detailed Summary

The ggml/llama.cpp project has updated its model repository to include new models LiquidAI/d1-2B and LiquidAI/d1-omni-2B, enhancing the available language processing capabilities. These updates were assisted by Claude Opus 5.5 and involve minor refactoring for better organization. The broader impact includes expanding the toolkit's versatility in handling diverse speech tasks.

Key Points

• • model : add LiquidAI/d1-2B and LiquidAI/d1-omni-2B
• • convert : keep the speech task templates out of the d1 GGUFs
• • small refactoring: no_batching