Skip to content

Commit

Permalink
update: deploy scripts
Browse files Browse the repository at this point in the history
  • Loading branch information
michaelfeil committed Jul 22, 2024
1 parent bc43ecc commit 6c5a79b
Showing 1 changed file with 8 additions and 5 deletions.
13 changes: 8 additions & 5 deletions docs/docs/deploy.md
Original file line number Diff line number Diff line change
Expand Up @@ -21,15 +21,18 @@ docker run -it --gpus all \
```
The cache path at inside the docker container is set by the environment variable `HF_HOME`.

## Runpod.io - Serverless
There is a dedicated guide on how deploy via Runpod Serverless.
https://github.com/runpod-workers/worker-infinity-text-embeddings/

## Modal Labs

A deployment example for usage within are located at repo, including a Github Actions Pipeline.

The example is located at [michaelfeil/infinity/tree/main/infra/modal](https://github.com/michaelfeil/infinity/tree/c84b15acc35d02005e6f69080a5ed7b0e23d0019/infra/modal).
Modal has sponsored compute credits for a free endpoint at https://infinity.modal.michaelfeil.eu - feel free to use.

Modal has sponsored compute credits for a GPU-powered endpoint at [infinity.modal.michaelfeil.eu](https://infinity.modal.michaelfeil.eu), which is freely available.

## Runpod.io - Serverless
There is a dedicated guide on how deploy via Runpod Serverless.
Find out how to deploy it via this Repo:
[github.com/runpod-workers/worker-infinity-text-embeddings](https://github.com/runpod-workers/worker-infinity-text-embeddings/)

## Bento - BentoInfinity
Example repo for deployment via Bento: https://github.com/bentoml/BentoInfinity
Expand Down

0 comments on commit 6c5a79b

Please sign in to comment.