ggml/llama.cpp releases: v0.4.1

TL;DR

The ggml/llama.cpp version 0.4.1 update enhances support for new models and improves handling in various functionalities, marking significant advancements in model integration and server management. This release is crucial for developers looking to optimize their AI applications using these specific models.

Detailed Summary

The ggml/llama.cpp project released version 0.4.1, which enhances support for new models including Maple 20B-A1B and Tencent Hy 4, while also improving various functionalities such as JSON schema handling and server management. This update impacts developers working with these language models by providing better integration and performance.

Key Points

• • Adds support for Maple 20B-A1B, Tencent Hy 4, and Spark2.5
• • Improves JSON schema handling, chat parsing, logging, and server child-process management
• • Updates ggml to v0.24.0
• • Changes `llama_sampler_chain_n()` return type to `int32_t`