-
Notifications
You must be signed in to change notification settings - Fork 84
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.
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
Bagatur/rfc pred eval inline #1236
base: main
Are you sure you want to change the base?
Conversation
Co-authored-by: Ankush Gola <[email protected]>
Co-authored-by: Bagatur <[email protected]>
…i/langsmith-sdk into isaac/multipartstuff
self._store_results = store_results | ||
|
||
@property | ||
def _example_count(self) -> int: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
we have a count endpoint now you could prob use for this?
yield experiment_row | ||
|
||
async for result in aitertools.aiter_with_concurrency( | ||
max_concurrency, predict_all(), _eager_consumption_timeout=0.001 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is there a way to push this concurrency down to the predict_all layer, so we grab an example, then concurrently run over each example? Does the aforward
and arun_evaluators
get run sequentially per thread?
No description provided.