llama.cpp
667d70d1 - metal : add `GGML_OP_CONV_TRANSPOSE_1D` kernels (ggml/1026)

Commit

339 days ago

metal : add `GGML_OP_CONV_TRANSPOSE_1D` kernels (ggml/1026) * wip * wip implementation f32 * kernel conv transpose 1d f32 working * initial commit

References

Author

PABannier

Committer

ggerganov

Parents