Change8

b10247

📦 llama-cppView on GitHub →
1 features🐛 1 fixes🔧 4 symbols

Summary

This release introduces dynamic allocation for split graph inputs in ggml, resolving crashes with wide MoE models. It also includes various pre-compiled binaries for different platforms and hardware accelerators.

✨ New Features

  • Use dynamic allocation for split graph inputs in ggml, replacing fixed-size arrays with dynamically allocated buffers in the backend scheduler.

🐛 Bug Fixes

  • Fixes crashes when loading wide MoE models (Gemma 4, Qwen MoE, Mixtral, DeepSeek) on multi-backend setups where graph splits exceed 30 input tensors.

Affected Symbols