llama.cpp
Revert "CUDA: add expert reduce kernel (#16857)"
#17100

Merged

Revert "CUDA: add expert reduce kernel (#16857)" #17100

am17an merged 1 commit into ggml-org:master from am17an:cuda-revert-moe-expert

Revert "CUDA: add expert reduce kernel (#16857)"

4d1daaf1

am17an requested a review from

slaren 218 days ago

am17an removed review request from

slaren 218 days ago

am17an requested a review from

JohannesGaessler 218 days ago

am17an requested a review from

slaren 218 days ago

github-actions added testing

github-actions added Nvidia GPU

github-actions added ggml

JohannesGaessler approved these changes on 2025-11-08

CISC commented on 2025-11-08

am17an merged 64fe17fb into master 217 days ago

am17an deleted the cuda-revert-moe-expert branch 217 days ago

Reviewers

JohannesGaessler

CISC

slaren

Assignees

No one assigned

Labels

testing Nvidia GPU ggml

Milestone

No milestone