llama.cpp
CUDA: batch out_prod broadcast (dps2>1) path with cublasSgemmBatched
#24426

Merged

CUDA: batch out_prod broadcast (dps2>1) path with cublasSgemmBatched #24426

ggerganov merged 1 commit into ggml-org:master from leonardHONG:cuda-outprod-batched

CUDA: batch out_prod broadcast (dps2>1) path with cublasSgemmBatched

55e7b37a

leonardHONG requested a review from

ggerganov 72 days ago

leonardHONG requested a review 72 days ago

github-actions added testing

github-actions added Nvidia GPU

github-actions added ggml

am17an approved these changes on 2026-06-25

am17an added merge ready

ggerganov merged f818065d into master 57 days ago

Reviewers

am17an

ggerganov

Assignees

No one assigned

Labels

testing Nvidia GPU ggml merge ready

Milestone

No milestone