docs: use Foundry Local SDK 2.2.1 for current setup

Keep setup instructions on the latest published patch release

Files changed, docs/my-website/docs/providers/foundry_local.md

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 2cf44fcd-0425-4d84-8ee0-ef774b78ec80
This commit is contained in:
Bhagirath Mehta 2026-10-21 13:56:07 -05:00
parent b010c3c13d
commit 8d9cf7a407
No known key found for this signature in database

View file

@ -21,13 +21,13 @@ https://github.com/microsoft/Foundry-Local
## Quick Start
Use [Foundry Local Python SDK 2.2.0](https://pypi.org/project/foundry-local-sdk/2.2.0/) to run models on-device. Foundry Local supports in-process inference, but LiteLLM uses its optional OpenAI-compatible HTTP service. Start that service and point `FOUNDRY_LOCAL_API_BASE` at its `/v1` URL.
Use [Foundry Local Python SDK 2.2.1](https://pypi.org/project/foundry-local-sdk/2.2.1/) to run models on-device. Foundry Local supports in-process inference, but LiteLLM uses its optional OpenAI-compatible HTTP service. Start that service and point `FOUNDRY_LOCAL_API_BASE` at its `/v1` URL.
<Tabs>
<TabItem value="python" label="Python SDK">
```bash
pip install foundry-local-sdk==2.2.0
pip install foundry-local-sdk==2.2.1
```
```python
@ -94,7 +94,7 @@ Keep this process running while LiteLLM uses the service. Configure the printed
</TabItem>
</Tabs>
### SDK 2.2.0 requirements
### SDK 2.2.1 requirements
The unified `foundry-local-sdk` Python wheel supports Windows x64, Linux x64/ARM64, and macOS Apple silicon. It requires Python 3.11 through 3.14. Windows wheels include the WinML runtime, so the separate `foundry-local-sdk-winml` package is no longer needed.