Skip to content

📄 Update docs for PR #89 #78

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

Open
pr-test1 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

📄 Update docs for PR #89 #78

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a18e1bc
docs: update quick-start.mdx for PR #89
pr-test1[bot] Aug 17, 2025
05c34a1
docs: update concepts/deployment.mdx for PR #89
pr-test1[bot] Aug 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 26 additions & 1 deletion concepts/deployment.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,6 +125,32 @@ models:
max_new_tokens: 250
```

### Specifying CPU Type

You can now specify the CPU type to be used during deployment by adding a `cpu_type` field to your YAML, or directly using the `--cpu` flag in the CLI:

**YAML field:**
```yaml
deployment: !Deployment
destination: aws
endpoint_name: cpu-type-demo
instance_count: 1
instance_type: ml.m5.xlarge
cpu_type: intel

models:
- !Model
id: google-bert/bert-base-uncased
source: huggingface
```

**CLI flag:**
```sh
magemaker --deploy your-model.yaml --cpu amd
```

> **Note:** The `--cpu` flag and corresponding YAML field let you control the CPU architecture (e.g., intel, amd, arm64) for your deployment on supported clouds/instance types.

## Cloud-Specific Instance Types

### AWS SageMaker Types
Expand Down Expand Up @@ -205,7 +231,6 @@ Choose your instance type based on your model's requirements:
Make sure you setup budget monitory and alerts to avoid unexpected charges.
</Warning>


## Troubleshooting Deployments

Common issues and their solutions:
Expand Down
13 changes: 13 additions & 0 deletions quick-start.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,15 @@ Supported providers:
- `--cloud azure` Azure Machine Learning deployment
- `--cloud all` Configure all three providers at the same time

You can also specify compute type with `--instance` and now **`--cpu`** for CPU selection:

```sh
magemaker --cloud aws --instance ml.m5.xlarge --cpu intel
```

- `--instance` Selects the instance type (e.g., `ml.m5.xlarge`, `g2-standard-12`, `Standard_DS3_v2`)
- `--cpu` Specifies CPU type (e.g., `intel`, `amd`) **(New!)**


### List Models

Expand Down Expand Up @@ -60,6 +69,7 @@ deployment: !Deployment
instance_type: ml.m5.xlarge
num_gpus: null
quantization: null
cpu: null # optionally specify cpu: intel or amd (new)
models:
- !Model
id: facebook/opt-125m
Expand All @@ -81,6 +91,7 @@ deployment: !Deployment
accelerator_type: NVIDIA_L4
num_gpus: null
quantization: null
cpu: null # optionally specify cpu: intel or amd (new)

models:
- !Model
Expand All @@ -100,6 +111,7 @@ deployment: !Deployment
endpoint_name: facebook-opt-test
instance_count: 1
instance_type: Standard_DS3_v2
cpu: null # optionally specify cpu: intel or amd (new)
models:
- !Model
id: facebook--opt-125m
Expand Down Expand Up @@ -184,3 +196,4 @@ You can reach us, faizan & jneid, at [support@slashml.com](mailto:support@slashm
If anything doesn't make sense or you have suggestions, do point them out at [magemaker.featurebase.app](https://magemaker.featurebase.app/).

We'd love to hear from you! We're excited to learn how we can make this more valuable for the community and welcome any and all feedback and suggestions.