llama.cpp
vulkan: Implement topk_moe fused shader, ported from CUDA
#16641

Merged

vulkan: Implement topk_moe fused shader, ported from CUDA #16641

0cc4m merged 1 commit into ggml-org:master from jeffbolznv:topk

vulkan: Implement topk_moe fused shader, ported from CUDA

e0f7fa91

jeffbolznv requested a review from

0cc4m 312 days ago

jeffbolznv requested a review from

ggerganov 312 days ago

jeffbolznv requested a review from

slaren 312 days ago

github-actions added Vulkan

github-actions added ggml

0cc4m approved these changes on 2025-10-18

0cc4m merged e56abd20 into master 312 days ago

Reviewers

0cc4m

ggerganov

slaren

Assignees

No one assigned

Labels

Vulkan ggml

Milestone

No milestone