Cameron

I see the tpu client was removed in 0.6.0, why did this happen?

Retry, Timeouts & Backoff support

1

It would be good to add the retry on failure for timeouts https://findwork.dev/blog/advanced-usage-python-requests-timeouts-retries-hooks/

add max tokens to health check

1

## Title health check should only need a minimal token completion call ## Relevant issues ## Type 🐛 Bug Fix ## Changes With the health check endpoint we really only...

bedrock: add apac claude support for cross region inferencing

6

## Title bedrock: add apac claude support ## Type 🐛 Bug Fix ## Changes Claude is now supported in APAC for cross inference profiles