Add Inference Spec & CI #23
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…rds compatibility with inference box
AlejandroEsquivel
requested review from
zsimjee,
dtam,
JosephCatrambone and
CalebCourier
zsimjee
approved these changes
Sep 25, 2024
Comment on lines
+42
to
+45
| def torch_device(self): | ||
| env = os.environ.get("env", "dev") | ||
| torch_device = "cuda" if env == "prod" else "cpu" | ||
| return torch_device |
There was a problem hiding this comment.
If we're bound to this for historical reasons I would let it slide, but I feel like names should be indicative of what they are. Could we call the environment variable 'inference_device' and pass it directly? If I read 'env' for something else dev but want to run on my local GPU I might make a bad mistake.
There was a problem hiding this comment.
this was left for reverse compatibility but now that we're fully switched over this is a good time to phase it out 👍🏼
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Added:
Example Running FastAPI with Inference Spec:
Example Running Ray Serve with Inference Spec:
# Refer to models-host repo for instructions if you don't have a GPU on the machine running ray serve pip install git+https://github.com/guardrails-ai/models-host@feat/adding-ray-setup serve run models_host.ray_serve:app