llama.cpp
6ad70c5a - ggml-cpu: arm64: Q4_K scale unroll and vectorization (#19108)

Commit

109 days ago

ggml-cpu: arm64: Q4_K scale unroll and vectorization (#19108)

References

#19108 - ggml-cpu: arm64: Q4_K repack (i8mm) scale unroll and vectorization

Author

Alcpz

Alcpz

Parents

Loading