llama.cpp
CPU/CUDA: fix GQA mul mat back, add CUDA support
#11380

Merged

CPU/CUDA: fix GQA mul mat back, add CUDA support #11380

JohannesGaessler merged 1 commit into ggml-org:master from JohannesGaessler:back-misc

github-actions added testing

github-actions added Nvidia GPU

github-actions added ggml

CPU/CUDA: fix (GQA) mul mat back, add CUDA support

ae4cca3e

JohannesGaessler force pushed to ae4cca3e 1 year ago

ggerganov approved these changes on 2025-01-24

JohannesGaessler merged 8137b4bb into master 1 year ago

Reviewers

ggerganov

Assignees

No one assigned

Labels

testing Nvidia GPU ggml

Milestone

No milestone