Change8

b10701

📦 llama-cppView on GitHub →
🐛 1 fixes🔧 2 symbols

Summary

This release addresses a critical bug in DFlash2 NVFP4 models by ensuring that Q, K, V, and output projection scales are correctly passed to attention operations, resolving issues with speculative token generation. Various pre-compiled binaries for different platforms and hardware are also provided.

🐛 Bug Fixes

  • Fixed an issue where DFlash2 NVFP4 draft models produced almost no accepted speculative tokens due to missing Q, K, V, and output projection scales not being passed to attention operations.

Affected Symbols