Skip to content

feat(ai): Add gen_ai.response.tokens_per_second attribute - #66

Merged
vgrozdanic merged 1 commit into
mainfrom
vg/tokens-per-second-attribute
Jul 2, 2025
Merged

vgrozdanic merged 1 commit into
mainfrom
vg/tokens-per-second-attribute

Conversation

@vgrozdanic

Copy link
Copy Markdown
Member

We have introduced this attribute in relay in getsentry/relay#4883.

This is a metric that Nvidia is using for benchmarking LLMs, and it is useful to know how fast LLM models are.

Closes TET-618: tokens per second

@vgrozdanic
vgrozdanic requested review from a team, AbhiPrasad, antonpirker and cleptric July 2, 2025 08:24
@vgrozdanic
vgrozdanic merged commit c4086d6 into main Jul 2, 2025
@vgrozdanic
vgrozdanic deleted the vg/tokens-per-second-attribute branch July 2, 2025 12:42
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