Skip to content

Swap out F16 for BF16 in Q8_1 activations to avoid overflowing values#22571

Draft
bartowski1182 wants to merge 4 commits into
ggml-org:masterfrom
bartowski1182:minimax
Draft

Swap out F16 for BF16 in Q8_1 activations to avoid overflowing values#22571
bartowski1182 wants to merge 4 commits into
ggml-org:masterfrom
bartowski1182:minimax

Replace casting with ggml_cuda_cast

8d93f39
Select commit
Loading
Failed to load commit list.
Sign in for the full log view
labeler
succeeded May 7, 2026 in 16s