[疑问] 自定义数据集跑不起来报错

[wangbairu]

[2026-03-29 01:04:32,658] [ais_bench] [INFO] Warmup finished Total Count: 1 Success Count: 0 Failed Count: 1
Failed Reasons:
+---------------+-------+
| Failed Reason | Count |
+---------------+-------+
| | 1 |
+---------------+-------+
Traceback (most recent call last):
File "/home/benchmark/ais_bench/benchmark/tasks/openicl_api_infer.py", line 704, in
raise e
File "/home/benchmark/ais_bench/benchmark/tasks/openicl_api_infer.py", line 701, in
inferencer.run(task_state_manager)
File "/home/benchmark/ais_bench/benchmark/tasks/openicl_api_infer.py", line 488, in run
self.warm_up(data_list, task_state_manager)
File "/home/benchmark/ais_bench/benchmark/tasks/openicl_api_infer.py", line 467, in warm_up
raise AISBenchRuntimeError(
ais_bench.benchmark.utils.logging.exceptions.AISBenchRuntimeError: [TINFER-RUNTIME-001]warmup failed. Exit task because all warmup requests failed, failed reasons: {'': 1} | Visit https://ais-bench-benchmark-rf.readthedocs.io/zh-cn/latest/faqs/error_codes.html#tinfer-runtime-001 for further help.
[2026-03-29 01:04:34,642] [ais_bench] [INFO] Inference tasks completed.
[2026-03-29 01:04:34,644] [ais_bench] [INFO] Summarizing performance results...
[2026-03-29 01:04:34,644] [ais_bench] [WARNING] Can't find details perf data of [vllm-api-stream-chat/gsm8k] in outputs/default/20260329_010406, use tmp cache data.
Traceback (most recent call last):
File "/usr/local/bin/ais_bench", line 33, in
sys.exit(load_entry_point('ais-bench-benchmark', 'console_scripts', 'ais_bench')())
File "/home/benchmark/ais_bench/benchmark/cli/main.py", line 6, in main
task_manager.run()
File "/home/benchmark/ais_bench/benchmark/cli/task_manager.py", line 39, in run
workflow_executor.execute()
File "/home/benchmark/ais_bench/benchmark/cli/workers.py", line 453, in execute
worker.do_work(cfg)
File "/home/benchmark/ais_bench/benchmark/cli/workers.py", line 430, in do_work
summarizer.summarize()
File "/home/benchmark/ais_bench/benchmark/summarizers/default_perf.py", line 427, in summarize
details_perf_datas = self._load_details_perf_data(
File "/home/benchmark/ais_bench/benchmark/summarizers/default_perf.py", line 251, in _load_details_perf_data
raise FileMatchError(
ais_bench.benchmark.utils.logging.exceptions.FileMatchError: [SUMM-FILE-001]can't find detail perf data file. Can't find any details perf data file in work_dir, please check outputs/default/20260329_010406. | Visit https://ais-bench-benchmark-rf.readthedocs.io/zh-cn/latest/faqs/error_codes.html#summ-file-001 for further help.

[github-actions]

🌟欢迎给AISBench benchmark测评工具提issue，您可以先尝试以下途径寻求issue的解决方法：

1. 【强烈推荐❤️‍🔥】确保issue描述完整后，可以试着将issue交给回答，deepwiki包含了和工具相关的所有知识库
2. 在 工具历史issue 中通过问题的关键日志片段或关键词检索相似issue
3. 在 官方文档 的搜索栏中通过问题的关键日志片段或关键词检索
4. 寻求仓库维护者的帮助（issue评论区中 @SJTUyh）

[github-actions]

🤖 基于AI机器人的issue内容完整性检查结果:

问题内容检查结果

检查状态

PASS

详细检查

• 疑问描述: COMPLETE

改进建议

所有内容已完备！

补充

👉 如果想重新检查，在评论区@issue_checker即可。

【强烈推荐❤️‍🔥】确保issue描述完整后，可以试着将issue交给回答，deepwiki包含了和工具相关的所有知识库

[github-actions]

🤖 issue content check result from AI robot:

Issue Content Check Result

Check Status

FAIL

Detailed Check

• Inquiry Description: INCOMPLETE

Improvement Suggestions

The "Inquiry Description" section is missing. The current issue body only contains error logs and tracebacks. To make the issue actionable and understandable, please provide the following information:

1. Problem Description: Clearly describe the issue you are encountering in your own words. What were you trying to achieve? What is the "自定义数据集" (custom dataset) you mentioned in the title?
2. Steps to Reproduce: Provide a clear, step-by-step guide on how to reproduce the issue. This should include:
   • The command you ran.
   • Details about your custom dataset (e.g., format, content, how it's used).
   • Any relevant configuration files or code snippets.
3. Expected Behavior: Describe what you expected to happen when you ran your custom dataset.
4. Actual Behavior: Explain what actually happened (beyond just the error messages).
5. Environment Information: Include details about your environment, such as:
   • Operating System.
   • Python version.
   • ais_bench version or how it was installed.
   • Any other relevant dependencies or hardware.

Additional Comments

The provided logs indicate a warmup failed error and a can't find detail perf data file error. While these are helpful, they are symptoms. A proper "Inquiry Description" from the user is essential to understand the root cause and provide assistance.

👉 If you want to re-check, please comment @issue_checker.

[Strongly recommended❤️‍🔥]Ensure your issue description is complete, then try to ask for help, as deepwiki contains all the knowledge related to the tool.