server/text_generation/models/seq2seq_lm.py · fcc2c5fcbf1bff5cdbba1508818650db13982ed2 · OpenDAS / text-generation-inference · GitLab

Find file Blame History Permalink

fix(server): Check for device type correctly when determining initial padding (#16) · 686cc667
Nick Hill authored Dec 30, 2022
```
AFAIK there is no torch device type called "gpu".
```
686cc667

seq2seq_lm.py 21.6 KB