llama.cpp
Avoid using __fp16 on ARM with old nvcc, fixes #10555
#10616

Merged

Avoid using __fp16 on ARM with old nvcc, fixes #10555 #10616

slaren merged 1 commit into ggml-org:master from frankier:fix-nvcc-cuda11-arm

github-actions added ggml

frankier force pushed 1 year ago

Avoid using __fp16 on ARM with old nvcc

dca39b08

frankier force pushed to dca39b08 1 year ago

slaren approved these changes on 2024-12-04

slaren merged cd2f37b3 into master 1 year ago

Reviewers

slaren

Assignees

No one assigned

Labels

ggml

Milestone

No milestone