Back to feed

b7833

Jan 25, 2026
Meta/llama.cppCLIvb7833

ggml-cpu: Use tiled FA for prompt-processing (#19012)

  • ggml-cpu: Use tiled FA for prompt-processing

the FA performance is gimped on CPU on long contexts because it essentially uses a vector kernel. This PR adds a tiled FA for PP. Perf tuning for tile sizes done on a AMD EPYC single-socket 64-c machine.

  • fix out of bounds for mask

  • skip rows where there are all masks

  • skip tile if mask is inf

  • store mask in worksize

  • check inf tile earlier

macOS/iOS:

Linux:

Windows:

openEuler: