llama : fix non-quantization of expert gating tensors #5754
ggerganov
merged
1 commit into
ggml-org:master
from
compilade:fix-no-quantize-ffn-gate-inp
llama : fix non-quantization of expert gating tensors
969be5d4
cebtenzzre
approved these changes
on 2024-02-27
ggerganov
approved these changes
on 2024-02-28
Login to write a write a comment.
Login via GitHub