]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
CUDA: add conv_2d_dw (llama/14265)
authorAman Gupta <redacted>
Fri, 20 Jun 2025 01:50:24 +0000 (09:50 +0800)
committerGeorgi Gerganov <redacted>
Fri, 20 Jun 2025 18:14:52 +0000 (21:14 +0300)
commit8909d55e6eff3aaa8371f4314ff57fdd4ad2577c
tree6aa1381f6b8fa7874185ab90bc7418a0ee05e8ad
parent790d48008b3e1012eff45099d9d781fe4dcf4510
CUDA: add conv_2d_dw (llama/14265)

* CUDA: add conv_2d_dw

* better naming

* simplify using template

* Review: fix operation ordering in ggml-cuda, use __forceinline__, use more const
src/ggml-cuda/conv2d-dw.cu [new file with mode: 0644]
src/ggml-cuda/conv2d-dw.cuh [new file with mode: 0644]
src/ggml-cuda/ggml-cuda.cu