Fix checking output limits for #114

huggingface / optimum-nvidia

Apache License 2.0

887 stars 86 forks source link

Fix checking output limits for #114 #115

Closed zaycev closed 5 months ago

zaycev commented 5 months ago

Fixes issue from #114

fxmarty commented 5 months ago

@zaycev Thank you for the fix, I'll merge as this makes the tests in https://github.com/huggingface/optimum-nvidia/pull/117 pass. Hopefully will get a patch release today

note: we should use public models and avoid requiring OPTIMUM_NVIDIA_HUB_READ_TOKEN secret that is not passed to PRs from forks on pull_request event.