llama.cpp
c2082d93 - ggml : add `GGML_PAD_REFLECT_1D` operation (ggml/1034)

Commit
276 days ago
ggml : add `GGML_PAD_REFLECT_1D` operation (ggml/1034) * ggml_pad_reflect_1d defined in header * implemented on CPU * called the forward pass * impl Metal kernel * added Metal kernel * added OP_PAD_REFLECT_1D in test-backend-ops.cpp * add test-pad-reflect-1d test case * test case support multiple backend
Author
Committer
Parents
Loading