PR #8495 CUDA: MMQ code deduplication + iquant support

CUDA: MMQ code deduplication + iquant support #8495

JohannesGaessler merged 2 commits into ggml-org:master from JohannesGaessler:cuda-mmq-deduplicate-4

github-actions added Nvidia GPU

github-actions added python

JohannesGaessler added Review Complexity : High

slaren approved these changes on 2024-07-17

JohannesGaessler force pushed 1 year ago

CUDA: MMQ code deduplication + iquant support

f0f71a5d

JohannesGaessler force pushed to f0f71a5d 1 year ago

1 less parallel job for CI build

0282b716

github-actions added devops

JohannesGaessler merged 69c487f4 into master 1 year ago

Reviewers

slaren

Assignees

No one assigned

Labels

Nvidia GPU python Review Complexity : High devops

Milestone

No milestone