]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 98e57ca)
cuda : extend GGML_OP_PAD to work with non-cont src0 (#19429)
authorGeorgi Gerganov <redacted>
Tue, 10 Feb 2026 06:07:16 +0000 (08:07 +0200)
committerGitHub <redacted>
Tue, 10 Feb 2026 06:07:16 +0000 (08:07 +0200)
commita0d585537cb7f0352c4859acbad64d5084dbe964
treea091c5d4c1b8022a5a2eb89976680f273d5a5890tree
parent98e57ca422c5adb33663a6406c2f2d5b7d255da7commit | diff
cuda : extend GGML_OP_PAD to work with non-cont src0 (#19429)

* cuda : extend GGML_OP_PAD to work with non-cont src0

* tests : add permuted pad
ggml/src/ggml-cpu/ops.cpp diff | blob | history
ggml/src/ggml-cuda/ggml-cuda.cu diff | blob | history
ggml/src/ggml-cuda/pad.cu diff | blob | history
tests/test-backend-ops.cpp diff | blob | history
Packaging of ggml-org/llama.cpp