llama.cpp
8380ecfb - ggml : fix unnecessary f32 -> f16 -> f32 casts (mmla) (#5951)

Commit

1 year ago

ggml : fix unnecessary f32 -> f16 -> f32 casts (mmla) (#5951)

References

#5951 - ggml : fix unnecessary f32 -> f16 -> f32 casts (mmla)

Author

ggerganov

ggerganov

Parents

Loading