-
Notifications
You must be signed in to change notification settings - Fork 23
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
chore: add optimum-neuron 0.0.18 image #55
Conversation
@dacorvo Could you please also modify |
Done |
@@ -21,7 +21,7 @@ | |||
{ | |||
"device": "inf2", | |||
"min_version": "0.0.16", | |||
"max_version": "0.0.17", | |||
"max_version": "0.0.18", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please also include 0.0.18 as a release candidate. I.e. put it into "releases"
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
OK: I did not know what to put there, so I did what was done in the other pull-request for TGI 1.4.0. Hope I did it right.
RUN pip3 install ./optimum-neuron | ||
|
||
# TGI base env | ||
ENV HUGGINGFACE_HUB_CACHE=/data \ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Sorry - another comment. This passes since optimum seems to be ok with being model data being downloaded to a smaller file system for the test case we have. But this might be a concern if there is a larger model that does not fit into \data
. Could you please change to \tmp
? cc. @nicolas, @david Holtz, @philschmid
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done.
8f69b78
to
7e4df73
Compare
Description of changes:
This adds a new docker image for Neuron X TGI based on
optimum-neuron
0.0.18.