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

Merged

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

ggerganov merged 3 commits into ggml-org:master from zihaomu:candidate1-concat-non-f32

cuda: support concat for scalar types

6e24dd07

zihaomu requested a review from

ggerganov 24 days ago

zihaomu requested a review 24 days ago

zihaomu changed the title ~~Cuda: support concat for scalar types~~ ggml: support concat for scalar types at cuda backend 24 days 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

am17an approved these changes on 2026-06-10

zihaomu requested a review 15 days ago

github-actions added Apple Metal

zihaomu force pushed from 0ff784c1 to f697a079 15 days ago

zihaomu commented on 2026-06-11

am17an approved these changes on 2026-06-11

am17an added merge ready

zihaomu force pushed from f697a079 to c96a285a 14 days ago

fix metal ci issue

c96a285a

ggerganov merged 85f99dca into master 14 days ago

Reviewers

am17an

JohannesGaessler

ggerganov

Assignees

No one assigned

Labels

testing Nvidia GPU ggml merge ready Apple Metal

Milestone

No milestone