You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I saw speculative decoding mentioned in #1539 . Is this supported for deployment to Android targets?
If I wanted to deploy Llama2-7b with TinyLlama as a draft model, how would I do that?
Would also be happy to contribute to the docs on this.
Thanks.
The text was updated successfully, but these errors were encountered:
I saw speculative decoding mentioned in #1539 . Is this supported for deployment to Android targets?
If I wanted to deploy Llama2-7b with TinyLlama as a draft model, how would I do that?
Would also be happy to contribute to the docs on this.
Thanks.
The text was updated successfully, but these errors were encountered: