Support benchmarking script by using real application trace #737
+587
−23
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
nwangfw
force-pushed
the
ning/gpu-optimizer-benchmark-with-real-prompts
branch
4 times, most recently
from
42214fb to
4761e31
Compare
Signed-off-by: Ning Wang <[email protected]>
Signed-off-by: Ning Wang <[email protected]>
Signed-off-by: Ning Wang <[email protected]>
Signed-off-by: Ning Wang <[email protected]>
Signed-off-by: Ning Wang <[email protected]>
Signed-off-by: Ning Wang <[email protected]>
Signed-off-by: Ning Wang <[email protected]>
nwangfw
force-pushed
the
ning/gpu-optimizer-benchmark-with-real-prompts
branch
from
4761e31 to
b02dabf
Compare
nwangfw
changed the title
|
@zhangjyr Can you help to review this PR? Thanks! |
zhangjyr
reviewed
Feb 25, 2025
| # Convert rate_start to integer (multiply by 100 and remove decimals) | ||
| req_rate=$(echo "$rate_start * 100" | bc | cut -d. -f1) | ||
| rate_limit_scaled=$(echo "$rate_limit * 100" | bc | cut -d. -f1) | ||
| while [[ $req_rate -le $rate_limit_scaled ]]; do |
There was a problem hiding this comment.
Is it because -le can compare integers only, so we need to *100? And I suppose 0.125 is also somehow supported (inaccurate is ok) by removing decimals? Just in case, I would suggest setting req_rate at least 0.01 to avoid 0.
| # synthetic_prompt = "hi " * config_input_len | ||
| # # assign timestamp to -1 for all requests | ||
| # requests.append((synthetic_prompt, config_input_len, config_output_len, -1)) | ||
| return [] |
There was a problem hiding this comment.
Why comment on this part? If no workload is provided, the benchmark will not work without a synthetic prompt.
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.
Pull Request Description
This PR adding benchmarking support by using real user application prompt traces in the heterogenous gpu story. This is a general benchmarking methods working for all models. It addresses the issue where the current fix benchmarking process may not be working for certain models or certain configuration settings (e.g., temperature)
Related Issues
Resolves: #722
Important: Before submitting, please complete the description above and review the checklist below.
Contribution Guidelines (Expand for Details)
We appreciate your contribution to aibrix! To ensure a smooth review process and maintain high code quality, please adhere to the following guidelines:
Pull Request Title Format
Your PR title should start with one of these prefixes to indicate the nature of the change:
[Bug]: Corrections to existing functionality[CI]: Changes to build process or CI pipeline[Docs]: Updates or additions to documentation[API]: Modifications to aibrix's API or interface[CLI]: Changes or additions to the Command Line Interface[Misc]: For changes not covered above (use sparingly)Note: For changes spanning multiple categories, use multiple prefixes in order of importance.
Submission Checklist
By submitting this PR, you confirm that you've read these guidelines and your changes align with the project's contribution standards.