Closed pquentin closed 3 months ago
A documentation preview will be available soon.
This pull request does not have a backport label. Could you fix it @pquentin? 🙏 To fixup this pull request, you need to add the backport labels for the needed branches, such as:
backport-/d./d
is the label to automatically backport to the /d./d
branch. /d
is the digit
NOTE: backport-skip
has been added to this pull request.I don't have the permission to add backports labels. Ideally this should be backported to 8.12, 8.13 and 8.14, since #2666 is on those versions, and the files it references are no longer reachable.
We maybe should do more, such as explain that linux-x86-64 is indeed the version optimized for "Intel® silicon".
It is mentioned in the docs https://www.elastic.co/guide/en/machine-learning/current/ml-nlp-e5.html
E5 has two versions: one cross-platform version which runs on any hardware and one version which is optimized for Intel® silicon. The Model Management > Trained Models page shows you which version of E5 is recommended to deploy based on your cluster’s hardware.
Right, I meant it's maybe not obvious that linux-x86-64
is the optimized version since it's not in the name anymore. But the docs now reads "For the optimized version, you need the following files in your system: ..." too so that's fine! Sorry for the noise.
Would you mind adding the backport labels? 8.12, 8.13 and 8.14
We also need a review from the docs team.
ping
I've also added the backport labels.
Thanks! I can't merge myself.
We maybe should do more, such as explain that
linux-x86-64
is indeed the version optimized for "Intel® silicon".