Skip to content

Conversation

Bslabe123
Copy link
Contributor

@Bslabe123 Bslabe123 commented Aug 8, 2024

Do not merge until #127

@Bslabe123 Bslabe123 requested a review from vipannalla as a code owner August 8, 2024 17:53
@@ -255,3 +255,12 @@ def get_request_output_length(self):

def get_request_success_count_metric(self):
return self._request_success_count.labels(id=self._id)

_total_tokens_in_current_batch = Gauge(
name="jetstream_total_tokens_in_current_batch",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We have padding in each batch, I feel this metric is not critical or useful. We more care about total response tokens per request. @JoeZijunZhou Please share your thoughts on this metrics.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Following up in the internal doc. The GKE team added this metric in the design doc.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants