Return usage for openai requests #1663
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ichernev
force-pushed
the
usage-v2
branch
2 times, most recently
from
2f0242a
to
7f0482c
Compare
|
Hi @ichernev, Thank you for your PR. Currently, we are trying to keep API server as minimal and encourage folks to use the OpenAI version. If you can limit this PR to just adding streaming support for OpenAI that would be great. We believe there's already support for usage in the non-streaming case. |
|
@simon-mo thanks for the feedback, I'll limit it to the streaming openai entrypoint. |
Include number of input, output and total tokens for regular and streaming openai requests.
ichernev
changed the title
|
@simon-mo code tweaks only openai endpoint now. Edited title & description. |
simon-mo
approved these changes
Nov 16, 2023
yxl
pushed a commit
to yxl/vllm
that referenced
this pull request
Nov 29, 2023
hongxiayang
pushed a commit
to hongxiayang/vllm
that referenced
this pull request
Feb 13, 2024
sjchoi1
pushed a commit
to casys-kaist-internal/vllm
that referenced
this pull request
May 7, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Include number of input, output and total tokens for openai regular and streaming requests.
OpenAI backend doesn't include this information for streaming requests, but it is a very requested feature.