Timur Ganiev

icon indicating a website link https://postmort3m.io icon indicating an email [email protected]

icon company @lukalabs icon location Yerevan, Armenia icon location NLP Engineer

Results 2 comments of Timur Ganiev

[Bug]: When loading two models into the same GPU with Docker, the second model requires more memory allocation than the first

Encountered the same issue. And seems like alew3 is right, the amount of consumed memory equals to the available VRAM.

[Frontend] Feature: support transcription API with language detection

Hey! Is there any updates?