]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: b9a3771)
ggml : remove redundant n_copies check when setting input/output (#17612)
authorDaniel Bevenius <redacted>
Tue, 2 Dec 2025 11:52:45 +0000 (12:52 +0100)
committerGitHub <redacted>
Tue, 2 Dec 2025 11:52:45 +0000 (12:52 +0100)
commit7f3a72a8ed796a135c81903546ef57c4aeda9f06
tree2956492330ddf37d9513fe3eee6dbf3f2e34f84dtree
parentb9a37717b0e93381e86ab24c1a367bea8946613bcommit | diff
ggml : remove redundant n_copies check when setting input/output (#17612)

This commit removes a redundant check for sched->n_copies > 1 when
setting input and output flags on tensor copies in
ggml_backend_sched_split_graph.

The motivation for this change is to clarify the code as the outer if
statement already performs this check.
ggml/src/ggml-backend.cpp diff | blob | history
Packaging of ggml-org/llama.cpp