-
Notifications
You must be signed in to change notification settings - Fork 204
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
Update HuggingFace DLC for TGI URI to 2.3 (latest) #852
base: main
Are you sure you want to change the base?
Update HuggingFace DLC for TGI URI to 2.3 (latest) #852
Conversation
/gcbrun |
/gcbrun |
tutorials-and-examples/genAI-LLM/deploying-mixtral-8x7b-instruct-L4-gpus/README.md
Outdated
Show resolved
Hide resolved
tutorials-and-examples/genAI-LLM/deploying-mistral-7b-instruct-L4gpus/README.md
Outdated
Show resolved
Hide resolved
tutorials-and-examples/genAI-LLM/serving-llama2-70b-on-l4-gpus/README.md
Outdated
Show resolved
Hide resolved
Co-authored-by: Raushan Kumar <[email protected]>
/gcbrun |
Still has issues check |
@alvarobartt should we revert to the old image to have the main branch sample in working state while we investigate. Once we have the fix we can update the image with additional changes ? |
Is this still the case @raushan2016? Should we instead update the image URI to point to the actual latest being |
Description
As a follow up PR of #816 recently merged, this PR contains the update to the latest version as of today of the Hugging Face DLC for TGI on Google Cloud, which is TGI 2.3.1 labelled as TGI 2.3.
Additionally, this PR also solves the
mountPath
issue as those are mounting/data
, whilst theHF_HOME
is set to/tmp
, leading to OOM in some scenarios where the/tmp
path runs out of disk space as the extra disk is assigned to/data
instead.Thanks in advance 🤗
cc @annapendleton