llama.cpp
cuda : relax tensor contiguity requirements for quantized concat
#25678

Merged

cuda : relax tensor contiguity requirements for quantized concat #25678

fairydreaming merged 3 commits into ggml-org:master from fairydreaming:cuda-q-concat-fix

cuda : relax tensor contiguity requirements for quantized concat

e3e3d126

tests : add test cases for non-contiguous quantized concat

63abbf07

ggml : relax contiguity requirements for quantized concat

d5a3ae64

fairydreaming requested a review from

ggerganov 23 hours ago

fairydreaming requested a review 23 hours ago

github-actions added testing

github-actions added ggml

github-actions added CUDA

am17an approved these changes on 2026-07-15

ggerganov approved these changes on 2026-07-15

fairydreaming merged a3e5b96a into master 6 hours ago

Reviewers

ggerganov

am17an

Assignees

No one assigned

Labels

testing ggml CUDA

Milestone

No milestone