This repository has been archived by the owner on Oct 11, 2024. It is now read-only.
Benchmark Fix : Fix JSON decode error #142
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
| raise ValueError(f"Cannot decode json body \n {body}") | ||
|
|
||
| @staticmethod | ||
| async def async_request_vllm( |
There was a problem hiding this comment.
no functional change this function except storing the response directly in the RequestFuncOutput
robertgshaw2-redhat
approved these changes
Mar 26, 2024
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Summary:
Bug : In benchmark_serving.py we use aiohttp's
iter_any()function for reading responses from the server.Sometimes, the data received from this function contains more than one JSON in it. This leads to a JSON decode error.
Fix : These JSONs essentially contain the generated text and the last of the JSONs has the entire generated text. The
fix is to identify the last JSON in the response data. The response data simply puts the JSONs next to each other. We identify occurrences of the string
{"text":in thebodyand use the JSON decoder to identify the last JSON.Test:
Manual testing