PR #29184 CUDA: fuse shared experts into MMVQ

CUDA: fuse shared experts into MMVQ #29184

ggerganov merged 3 commits into master from aman/shared-exp-fusion

am17an requested a review from

ggerganov 22 days ago

am17an requested a review 22 days ago

github-actions added testing

github-actions added ggml

github-actions added CUDA

ynankani commented on 2026-09-21

JohannesGaessler commented on 2026-09-29

JohannesGaessler approved these changes on 2026-10-01

am17an added merge ready

CUDA: fuse shared experts into MMVQ

2d3b7560

check if buffer is null

7a60a17d

move stride_col_dst to fusion args

7a080b9d

am17an force pushed from e12b6832 to 7a080b9d 10 days ago

ggerganov merged bed0a856 into master 10 days ago

ggerganov deleted the aman/shared-exp-fusion branch 10 days ago

Reviewers

JohannesGaessler

ynankani

ggerganov

Assignees

No one assigned

Labels

testing ggml merge ready CUDA

Milestone

No milestone