Change8

b10632

📦 llama-cppView on GitHub →
1 features🔧 2 symbols

Summary

Introduced chunked SSD MMA for Mamba-2 prefill optimization on Metal, improving performance by dropping the scalar SSD path and utilizing MMA with a sequential tail. Several constants and internal states have been refactored for clarity and efficiency.

Migration Steps

  1. Remove scalar SSD path; MMA + sequential tail is now used.
  2. Remove state_from_dst and rename CS and NSG constants.

✨ New Features

  • Added chunked SSD MMA for Mamba-2 prefill optimization on Metal.

Affected Symbols