| 【BugFix】Fix pressure mode not stop when time arrive& stable summary unexpected due to interval offset (#42)
* fix pressure bug
* fix commit
* fix pressure interval bug
* fix concurrency exit multi request
* use full uuid
* use process lock
* remove global data index function
* padding indexes use global_indexes
* ut bug fix
* fix multi process data id incorrect bug | 5 个月前 |
| 【Feature】add SWE-bench eval task, dataset loader, and summarizer integration (#240)
* util adapter
* adapter swebench eval
---------
Co-authored-by: zhanggaohua@huawei.com <GaoHua>
Co-authored-by: Jianxin <keith_wwa@163.com> | 1 个月前 |
| support mmlu_pro overalll score (#216)
Co-authored-by: SJTUyh <yh_silence@alumni.sjtu.edu.cn> | 2 个月前 |
| 【Feature】add SWE-bench eval task, dataset loader, and summarizer integration (#240)
* util adapter
* adapter swebench eval
---------
Co-authored-by: zhanggaohua@huawei.com <GaoHua>
Co-authored-by: Jianxin <keith_wwa@163.com> | 1 个月前 |
| Fix the issue where TTFT and TPOT have no data when running Kimi2.5 i… (#153)
* Fix the issue where TTFT and TPOT have no data when running Kimi2.5 in a PD separation scenario.
* Apply suggestion from @gemini-code-assist[bot]
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
---------
Co-authored-by: zhang GaoHua <73919261+GaoHuaZhang@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> | 2 个月前 |
| [For merge][part 1] Support Gedit Evaluate (#159)
* add cli models openicl tasks
* review fix
---------
Co-authored-by: SJTUyh <yh_silence@alumni.sjtu.edu.cn> | 2 个月前 |
| refactor: add logs and ut types (#14)
* refactor: rename cofig error and delete unused logging
* fix: delete used import
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: zhongzhoutan <cqyzdp1@163.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> | 6 个月前 |
| fix monitor not run in back in some case (#44)
| 5 个月前 |
| 【Feature】add SWE-bench eval task, dataset loader, and summarizer integration (#240)
* util adapter
* adapter swebench eval
---------
Co-authored-by: zhanggaohua@huawei.com <GaoHua>
Co-authored-by: Jianxin <keith_wwa@163.com> | 1 个月前 |
| 【Feature】Support SWE-Bench benchmark pipeline and Mini SWE Agent integration (#241)
* util adapter
* adapter swebench eval
* adapter mini swe agent
---------
Co-authored-by: zhanggaohua@huawei.com <GaoHua> | 1 个月前 |
| util adapter (#239)
Co-authored-by: zhanggaohua@huawei.com <GaoHua> | 1 个月前 |
| [other] Update the default version name of AISBench benchmark to 3.1.0 (#116)
* change offical default version from 3.0.0 to 3.1.0
---------
Co-authored-by: SJTUyh <yh_silence@alumni.sjtu.edu.cn> | 4 个月前 |
| init repo content
| 6 个月前 |
| refactor: add logs and ut types (#14)
* refactor: rename cofig error and delete unused logging
* fix: delete used import
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: zhongzhoutan <cqyzdp1@163.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> | 6 个月前 |