llama-stack-mirror/llama_stack/providers/remote/inference/bedrock
skamenan7 c752209ee4 fix bedrock inference profile IDs for AWS regions
AWS switched to requiring region-prefixed inference profile IDs instead of
foundation model IDs. 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 region.

Handles edge cases like ARNs, case sensitivity, and None regions.
This fixes the ValidationException error when using on-demand throughput.
2025-09-10 09:18:07 -04:00
..
__init__.py feat(pre-commit): enhance pre-commit hooks with additional checks (#2014) 2025-04-30 11:35:49 -07:00
bedrock.py fix bedrock inference profile IDs for AWS regions 2025-09-10 09:18:07 -04:00
config.py feat(pre-commit): enhance pre-commit hooks with additional checks (#2014) 2025-04-30 11:35:49 -07:00
models.py ci: test safety with starter (#2628) 2025-07-09 16:53:50 +02:00