Change8

b10713

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

Summary

This release includes an update to ggml to add MUL_MAT to operations that may require additional memory for WebGPU. Various pre-compiled binaries for different platforms and configurations are also provided.

🐛 Bug Fixes

  • ggml: Added MUL_MAT to the list of operations that may require additional memory for WebGPU.

Affected Symbols