]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
`ggml_cuda_cpy` support for 4d tensors and float16->float32 upcasting (ggml/686)
authorJohn Balis <redacted>
Mon, 29 Jan 2024 12:37:33 +0000 (06:37 -0600)
committerGeorgi Gerganov <redacted>
Tue, 30 Jan 2024 19:27:59 +0000 (21:27 +0200)
commitbaa190446ac264640238a8517e1885fa053db0f8
treeb1d0114a3c2ccd43dd51e016c567e275898fd23f
parent8f5220d81fad6db7f221f3d977b15b8b493641f3
`ggml_cuda_cpy` support for 4d tensors and float16->float32 upcasting (ggml/686)

* added cuda float16->float32 upcasting to ggml_cuda_cpy

* added ability to copy 4d tensors with the cuda backend

* added tests for float16_>float32 upcast and 4d tensor cuda copys

* added 4d copy test for float32->float16 copy

* applied patch suggested by @iamlemec

* simplify cpy tests

---------

Co-authored-by: slaren <redacted>
ggml-cuda.cu