Official @ggml_org shipped llama.cpp v0.4.1: adds Maple 20B-A1B, Tencent Hy 4, and Spark2.5 support; improves Kimi-K3 rollback, JSON schema handling, qwen3-coder complex-type parsing, and MCP/multimodal fixes; updates ggml to v0.24.0. Release notes: ggml-org/llama.cpp v0.4.1.

Key Takeaways

  • βœ“Official llama.cpp v0.4.1 adds Maple 20B-A1B, Tencent Hy 4, and Spark2.5.
  • βœ“Improves qwen3-coder parsing, Kimi-K3 rollback, JSON schema, and multimodal/server stability.
  • βœ“ggml bumps to v0.24.0; notes on ggml-org/llama.cpp v0.4.1.
ADSponsored