News for hackers. Stuff that matters.

A comment on Ultra Fast Bert. Parent comment

Re:Ultra Fast Bert by entropicdrifter on Wednesday November 22, 2023 @01:09PM (#38382782)
And potentially for distributing a model across several devices at inference time. You could devote a cluster of smaller/weaker machines to inference.
[ Parent | on HN ]
Re:Ultra Fast Bert by sroussey on Wednesday November 22, 2023 @02:16PM (#38383767)
You can do that today, the only advantage today though is being able to fix the model in memory. It’s sequential and slower due to communication costs, though batching might be faster?
[ Parent | on HN ]