mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
2838d5a20f
Fixes #3370 AWS switched to requiring region-prefixed inference profile IDs instead of foundation model IDs for on-demand throughput. This was causing ValidationException errors. Added auto-detection based on boto3 client region to convert model IDs like meta.llama3-1-70b-instruct-v1:0 to us.meta.llama3-1-70b-instruct-v1:0 depending on the detected region. Also handles edge cases like ARNs, case insensitive regions, and None regions. Tested with this request. ```json { "model_id": "meta.llama3-1-8b-instruct-v1:0", "messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "tell me a riddle" } ], "sampling_params": { "strategy": { "type": "top_p", "temperature": 0.7, "top_p": 0.9 }, "max_tokens": 512 } } ``` <img width="1488" height="878" alt="image" src="https://github.com/user-attachments/assets/0d61beec-3869-4a31-8f37-9f554c280b88" /> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| bedrock.py | ||
| config.py | ||
| models.py | ||