search

huggingface / optimum-nvidia

Apache License 2.0
844 stars 83 forks source link

Test batched causallm inference #117

Closed fxmarty closed 3 months ago

fxmarty commented 3 months ago

As per title.

fxmarty commented 3 months ago

Looks good, we should bump to Transformers 4.39 for the CI OOM