[CI] add API evaluation test #3987
Open
Conversation
This file contains hidden or 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
lvhan028
reviewed
Sep 19, 2025
autotest/utils/config_utils.py
Outdated
| if len(model_list) > 0: | ||
|
|
||
| if tp_num > 1: | ||
| communicators = ['native', 'nccl'] |
There was a problem hiding this comment.
Please change native to cuda-ipc, since we are going to deprecate native, which is alias to cuda-ipc
lvhan028
reviewed
Sep 19, 2025
| @@ -0,0 +1,90 @@ | |||
| import pytest | |||
There was a problem hiding this comment.
This file is a copy of test_api_evaluate_pytorch.
Could you provide a unified test_api_evaluation.py?
lvhan028
reviewed
Sep 19, 2025
lvhan028
reviewed
Sep 19, 2025
.github/workflows/api_eva.yml
Outdated
| @@ -0,0 +1,137 @@ | |||
| name: api_eva | |||
There was a problem hiding this comment.
may use api_eva and rename the filename api_eval.yml
lvhan028
reviewed
Sep 19, 2025
lvhan028
reviewed
Sep 19, 2025
autotest/utils/evaluate_utils.py
Outdated
Comment on lines
16
to
37
| if work_dir and os.path.exists(work_dir): | ||
| try: | ||
| summary_dirs = glob.glob(os.path.join(work_dir, '*', 'summary')) | ||
| if summary_dirs: | ||
| summary_dir = summary_dirs[0] | ||
| csv_files = glob.glob(os.path.join(summary_dir, 'summary_*.csv')) | ||
| if csv_files: | ||
| csv_file = sorted(csv_files)[-1] | ||
| if os.path.exists(csv_file): | ||
| with open(csv_file, 'r') as f: | ||
| reader = csv.reader(f) | ||
| next(reader) | ||
| for row in reader: | ||
| if len(row) >= 5 and row[4]: | ||
| dataset = row[0] | ||
| metric_value = row[4] | ||
| try: | ||
| metrics[dataset] = f'{float(metric_value):.2f}' | ||
| except ValueError: | ||
| metrics[dataset] = metric_value | ||
| except Exception as e: | ||
| print(f'Error reading metrics: {str(e)}') |
There was a problem hiding this comment.
Can we simplify this code snippet? The indent is too deep
lvhan028
reviewed
Sep 19, 2025
autotest/utils/evaluate_utils.py
Outdated
Comment on lines
46
to
53
| write_header = False | ||
| if not os.path.exists(summary_file) or os.path.getsize(summary_file) == 0: | ||
| write_header = True | ||
| else: | ||
| with open(summary_file, 'r') as f: | ||
| first_lines = f.read(200) | ||
| if '| Model | Backend | TP | Status | mmlu | gsm8k |' not in first_lines: | ||
| write_header = True |
There was a problem hiding this comment.
Can we change it to the following?
write_header = not os.path.exists(summary_file) or os.path.getsize(summary_file) == 0
May kindly let us know in what cases the first line are not the "| Model | Backend | TP | Status | mmlu | gsm8k |"
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.
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily receiving feedbacks. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.
Motivation
Please describe the motivation of this PR and the goal you want to achieve through this PR.
Modification
Please briefly describe what modification is made in this PR.
BC-breaking (Optional)
Does the modification introduce changes that break the backward-compatibility of the downstream repositories?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.
Use cases (Optional)
If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.
Checklist