llama.cpp
ggml-webgpu: fix minimax-m3 crash on webgpu by adding F16 REPEAT
#26307

Merged

ggml-webgpu: fix minimax-m3 crash on webgpu by adding F16 REPEAT #26307

fairydreaming merged 1 commit into ggml-org:master from yomaytk:fix-webgpu-ci

github-actions added testing

github-actions added ggml

github-actions added WebGPU

Add F16 support for repeat

c9fa4ceb

yomaytk force pushed to c9fa4ceb 97 days ago

yomaytk marked this pull request as ready for review 97 days ago

yomaytk requested a review from

ggerganov 97 days ago

yomaytk requested a review 97 days ago

nikwen approved these changes on 2026-07-31

fairydreaming approved these changes on 2026-08-01

reeselevine approved these changes on 2026-08-01

fairydreaming merged 7a2db1a0 into master 94 days ago

Reviewers

reeselevine

fairydreaming

nikwen

ggerganov

Assignees

No one assigned

Labels

testing ggml WebGPU

Milestone

No milestone