mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-22 23:03:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

batch: use tensors for outputs (#12185)

Browse Source 
this cleans up the model interface slightly without too much impact in
other areas
This commit is contained in:
Michael Yang
2025-09-15 14:33:06 -07:00
committed by GitHub
parent 92b96d54ef
commit 6f7117145f
14 changed files with 27 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
model/models/mllama/model.go
View File

@@ -107,10 +107,9 @@ func (m *Model) Forward(ctx ml.Context, batch input.Batch) (ml.Tensor, error) {
}
positions := ctx.Input().FromIntSlice(batch.Positions, len(batch.Positions))
outputs := ctx.Input().FromIntSlice(batch.Outputs, len(batch.Outputs))
// TODO: attention mask, cross attention mask
return m.TextModel.Forward(ctx, batch.Inputs, positions, outputs, crossAttentionStates, nil, m.Cache.(*kvcache.WrapperCache)), nil
return m.TextModel.Forward(ctx, batch.Inputs, positions, batch.Outputs, crossAttentionStates, nil, m.Cache.(*kvcache.WrapperCache)), nil
}
func init() {