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.

Sign up for GitHub

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

Jump to bottom

Override ModelDeploymentSpec of registered models #526

Merged
merged 2 commits into from
Jan 18, 2024
Merged

Override ModelDeploymentSpec of registered models #526

merged 2 commits into from
Jan 18, 2024

Commits on Jan 18, 2024

  1. Override ModelDeploymentSpec of registered models 

    This PR allows users to override the deployment spec of registered models.
For example, registered models and their deployment spec can be overridden as follows:

```yaml
TinyLlama/TinyLlama-1.1B-Chat-v1.0:
    runtime_env: custom-gpu
    deployment:
      resources:
        device: auto
        device_memory: 3Gi
```

In this example, the deployment resources for the model
`TinyLlama/TinyLlama-1.1B-Chat-v1.0` will be overridden to use
the `custom-gpu` runtime environment and `3Gi` of device memory.
    @spillai
    spillai committed Jan 18, 2024
    Configuration menu
    Copy the full SHA
    a2e1869 View commit details
    Browse the repository at this point in the history

  2. Fix bug with num_replicas on .add)

    @spillai
    spillai committed Jan 18, 2024
    Configuration menu
    Copy the full SHA
    ff2c255 View commit details
    Browse the repository at this point in the history