llama.cpp
ggml-cpu(s390x): vectorize fp32 to fp16 conversion
#30157

Merged

ggml-cpu(s390x): vectorize fp32 to fp16 conversion #30157

ggerganov merged 1 commit into ggml-org:master from taronaeo:feat/s390x-fp16-convert

ggml-cpu: vectorize fp32 to fp16 conversion

b37399a1

taronaeo requested a review from

ggerganov 32 days ago

taronaeo added merge ready

github-actions added ggml

ggerganov merged 2bbca8f2 into master 30 days ago

Reviewers

ggerganov

Assignees

No one assigned

Labels

ggml merge ready

Milestone

No milestone