Skip to content

ci: rm GGML_HIP_ROCWMMA_FATTN - #26760

Merged
taronaeo merged 1 commit into
ggml-org:masterfrom
taronaeo:fix/ci-gpu-rocm-macros
Aug 9, 2026
Merged

ci: rm GGML_HIP_ROCWMMA_FATTN#26760
taronaeo merged 1 commit into
ggml-org:masterfrom
taronaeo:fix/ci-gpu-rocm-macros

Conversation

@taronaeo

@taronaeo taronaeo commented Aug 8, 2026

Copy link
Copy Markdown
Member

Overview

-DGGML_HIP_ROCWMMA_FATTN option was removed in #26046 but there were still traces of this in the codebase. While working on the gpu-rocm CI, I didn't notice it was dead code and thus removing it now, together with all other references.

Requirements

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
@taronaeo
taronaeo requested review from a team, ggerganov and ngxson as code owners August 8, 2026 08:18
@github-actions github-actions Bot added the devops improvements to build systems and github actions label Aug 8, 2026
@taronaeo

taronaeo commented Aug 8, 2026

Copy link
Copy Markdown
Member Author

cc: @jimw567

@taronaeo taronaeo added the merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge. label Aug 8, 2026
@jimw567

jimw567 commented Aug 8, 2026

Copy link
Copy Markdown
Contributor

cc: @jimw567

Thanks. Have been waiting for this flag gone for a while :)

@taronaeo
taronaeo merged commit 61141f1 into ggml-org:master Aug 9, 2026
6 checks passed
Anbeeld added a commit to Anbeeld/beellama.cpp that referenced this pull request Aug 10, 2026
Drops the GGML_HIP_ROCWMMA_FATTN=ON lines resurrected by the v0.4.2
merge (the option was removed upstream in ggml-org#26760 and no longer exists
in ggml), restores the static-test ban against it, and picks up the
Windows HIP build hardening: N-1 build parallelism against clang OOM
and ccache saves skipped on failed builds.
miltos22 pushed a commit to miltos22/llama.cpp-wackMall-merge-request that referenced this pull request Aug 10, 2026
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
huaxel pushed a commit to huaxel/CachyLLama that referenced this pull request Aug 12, 2026
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
brittlewis12 pushed a commit to brittlewis12/llama.cpp that referenced this pull request Aug 17, 2026
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
thecodacus pushed a commit to thecodacus/llama.cpp that referenced this pull request Sep 7, 2026
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
zbrad pushed a commit to zbrad/llama.cpp that referenced this pull request Sep 10, 2026
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

devops improvements to build systems and github actions merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants