llama.cpp
Add a workaround for compilation with ROCWMMA_FATTN and gfx9
#19461

Merged

Add a workaround for compilation with ROCWMMA_FATTN and gfx9 #19461

JohannesGaessler merged 1 commit into ggml-org:master from superm1:superm1/rocwmma-workaround

Add a workaround for compilation with ROCWMMA_FATTN and gfx9

cc5a595f

IMbackK approved these changes on 2026-02-09

IMbackK requested a review from

JohannesGaessler 108 days ago

github-actions added Nvidia GPU

github-actions added ggml

JohannesGaessler approved these changes on 2026-02-09

JohannesGaessler merged 6845f7f8 into master 105 days ago

Reviewers

JohannesGaessler

IMbackK

Assignees

No one assigned

Labels

Nvidia GPU ggml

Milestone

No milestone