llama.cpp
ggml: support concat for scalar types at cuda backend
#24011

Open

ggml: support concat for scalar types at cuda backend #24011

zihaomu wants to merge 2 commits into ggml-org:master from zihaomu:candidate1-concat-non-f32

cuda: support concat for scalar types

6e24dd07

zihaomu requested a review from

ggerganov 1 day ago

zihaomu requested a review 1 day ago

zihaomu changed the title ~~Cuda: support concat for scalar types~~ ggml: support concat for scalar types at cuda backend 1 day ago

github-actions added testing

github-actions added Nvidia GPU

github-actions added ggml

JohannesGaessler commented on 2026-06-02

Update concat.cu

38dca84a

JohannesGaessler approved these changes on 2026-06-02

Reviewers

JohannesGaessler

ggerganov

Assignees

No one assigned

Labels

testing Nvidia GPU ggml

Milestone

No milestone