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
- βOfficial llama.cpp v0.4.1 adds Maple 20B-A1B, Tencent Hy 4, and Spark2.5.
- βImproves qwen3-coder parsing, Kimi-K3 rollback, JSON schema, and multimodal/server stability.
- βggml bumps to v0.24.0; notes on ggml-org/llama.cpp v0.4.1.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.