Skip to content
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

xpu/cpu: docker images referenced in documentation do not exist #2530

Open
dvrogozh opened this issue Sep 17, 2024 · 3 comments
Open

xpu/cpu: docker images referenced in documentation do not exist #2530

dvrogozh opened this issue Sep 17, 2024 · 3 comments

Comments

@dvrogozh
Copy link
Contributor

xpu and cpu Intel images referenced in documentation do not exist:

$ docker pull ghcr.io/huggingface/text-generation-inference:2.2.0-intel-cpu
Error response from daemon: manifest unknown
(pytorch.xpu) dvrogozh@willow-spr03:~/git/huggingface/text-generation-inference$ docker pull ghcr.io/huggingface/text-generation-inference:2.2.0-intel-xpu
Error response from daemon: manifest unknown

That's regression after this PR got merged 3 weeks ago:

since older named image does exist:

$ docker pull ghcr.io/huggingface/text-generation-inference:2.2.0-intel
2.2.0-intel: Pulling from huggingface/text-generation-inference
Digest: sha256:d54e6dd00462c705e86a4437bc4655e56da2de46529b2f89d21c1706f62567ae
Status: Image is up to date for ghcr.io/huggingface/text-generation-inference:2.2.0-intel
ghcr.io/huggingface/text-generation-inference:2.2.0-intel

@sywangyi @yao-matrix @Narsil

@dvrogozh
Copy link
Contributor Author

Also, considering that the PR did propose a name change for Intel image. Can instruction and docker images clearly reflect that these images are IPEX based? Please note that XPU support is available in upstream pytorch and it's actually confusing to download image with the generic XPU name in it to find out that it actually has IPEX inside.

@sywangyi
Copy link
Contributor

try
docker pull ghcr.io/huggingface/text-generation-inference:latest-intel-xpu

and
docker pull ghcr.io/huggingface/text-generation-inference:latest-intel-cpu

@dvrogozh
Copy link
Contributor Author

try
docker pull ghcr.io/huggingface/text-generation-inference:latest-intel-xpu
and
docker pull ghcr.io/huggingface/text-generation-inference:latest-intel-cpu

@sywangyi : these two commands work, but they are not documented either.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants