-
Notifications
You must be signed in to change notification settings - Fork 376
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add benchmark report generated in summary #1419
Merged
lvhan028
merged 20 commits into
InternLM:main
from
zhulinJulia24:benchmark_report_generate
Apr 15, 2024
Merged
Add benchmark report generated in summary #1419
lvhan028
merged 20 commits into
InternLM:main
from
zhulinJulia24:benchmark_report_generate
Apr 15, 2024
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
RunningLeon
reviewed
Apr 11, 2024
@zhulinJulia24 hi, there are too many digits after the zero point for RPS/RPM columns, can you make it nicer with three digits? |
|
RunningLeon
approved these changes
Apr 15, 2024
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
lvhan028
reviewed
Apr 15, 2024
lvhan028
reviewed
Apr 15, 2024
嗯 刚才写错了 发现了 已经改了
---- Replied Message ----
| From | Lyu ***@***.***> |
| Date | 04/15/2024 12:03 |
| To | ***@***.***> |
| Cc | ***@***.***>***@***.***> |
| Subject | Re: [InternLM/lmdeploy] Add benchmark report generated in summary (PR #1419) |
@lvhan028 commented on this pull request.
In .github/workflows/benchmark.yml:
@@ -160,10 +160,7 @@ jobs:
rm -rf ${result_dir}
mkdir ${result_dir}
export CUDA_VISIBLE_DEVICES=6,7
- python3 benchmark/profile_generation.py $MODEL_PATH $MAX_ENTRY_COUNT $MODEL_FORMAT $TP_INFO -c 1 --csv ${result_dir}/generation_batch1.csv > ${result_dir}/generation_batch1.log
- python3 benchmark/profile_generation.py $MODEL_PATH $MAX_ENTRY_COUNT $MODEL_FORMAT $TP_INFO -c 16 -ct 2048 -pt 2048 --csv ${result_dir}/generation_batch16.csv > ${result_dir}/generation_batch16.log
- python3 benchmark/profile_generation.py $MODEL_PATH $MAX_ENTRY_COUNT $MODEL_FORMAT $TP_INFO -c 32 -ct 128 2048 -pt 2048 128 --csv ${result_dir}/generation_batch32.csv > ${result_dir}/generation_batch32.log
- python3 benchmark/profile_generation.py $MODEL_PATH $MAX_ENTRY_COUNT $MODEL_FORMAT $TP_INFO -c 64 -ct 128 -pt 128 --csv ${result_dir}/generation_batch64.csv > ${result_dir}/generation_batch64.log
+ python3 benchmark/profile_generation.py $MODEL_PATH $MAX_ENTRY_COUNT $MODEL_FORMAT $TP_INFO -c 128 128 2048 -ct 128 2048 128 -pt 128 --csv ${result_dir}/generation_batch64.csv > ${result_dir}/generation_batch64.log
不是的。是-c 128 (表示concurrency)
-ct 128 2048 128 -pt 128 2048 128
文件名:generation_batch128.csv
$MODEL_PATH 都有哪些呢?如果测试了多个模型,那么 --csv 要有所区别了
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
lvhan028
approved these changes
Apr 15, 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.
add benchmark report generated in summary. test report is https://github.com/zhulinJulia24/lmdeploy/actions/runs/8628646975
![image](https://private-user-images.githubusercontent.com/145004780/321226610-14e21ebd-a089-4778-9c89-5a39e4551072.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjYxNTc0MzksIm5iZiI6MTcyNjE1NzEzOSwicGF0aCI6Ii8xNDUwMDQ3ODAvMzIxMjI2NjEwLTE0ZTIxZWJkLWEwODktNDc3OC05Yzg5LTVhMzllNDU1MTA3Mi5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwOTEyJTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDkxMlQxNjA1MzlaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT0yN2JmOWMyZjJmYWEyMzUwOWU5OTBjNTY3OGI0MDA0ZTM0Yjc1ODI4YTA0Yjc3ZTlkNDZlZDBjMDcxNmZjYTdkJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.5PzcXMpgA9KA3BTxCzvzr-B9zz0Fq3-2TTDjfqOqepc)
add -x in pr_test, when one testcase run fail pytest will fail.
change model path into local path, because nfs is not stable