[新需求] 新增aclgraph独立工具类
Co-authored-by: Dawn952<zhaojunbo13@huawei.com>
# message auto-generated for no-merge-commit merge:
!160 merge independent_utils_and_files into dev
[新需求] 新增aclgraph独立工具类
Created-by: Dawn952
Commit-by: Dawn952
Merged-by: ascend-robot
Description: <!--
PR描述模板更新日期：20251225
-->
# 合入背景
> 补充aclgraph需要的工具文件。\
> 注意：Fixes #ISSUE ID会自动关闭issue，如问题部分解决请不要使用Fixes，可以用Fix part of #ISSUE ID替代.
Fix part of #103
# 修改内容
> 新增了hf.py 用于做huggingface相关校验；新增了url.py 用于屏蔽报错信息中的url信息； 新增了models.__init__ 作为model_runner调用的入口；
新增load_config.py 提供LoadConfig类型； 修改了huggingface_config.py 增加部分参数定义，增加校验。
# 资料变更
> 不涉及。
# 接口变更
> 不涉及。
# 测试结果
> 在aclgraph联调分支完成验证。\
- DeepSeek-V3.2-1201-w8a8 A3 16卡
```
curl -curl -H "Accept: application/json" -H "Content-type: application/json" -X POST -d '{
"model": "ds_v3.2",
"prompt": "What is the best model in China",
"stream": false,
"ignore_eos": false,
"max_tokens": 132
}' http://141.61.105.118:1025/v1/completions
{"id":"endpoint_common_1","object":"text_completion","created":1767753398,"model":"ds_v3.2","choices":[{"index":0,"text":"? In Taiwan? In New Zealand? In Canada? In\nJapan? In the United States? In Israel? In Singapore?\n\nSome of the answers to these questions have to be in the form of what the\nbest model of government and governance is in each country.\n\nThe best model is that one which will yield in the country the best\nconditions, the best environment, the best system, the best results, the best\noutputs, the best outcomes.\n\nThe best model is that one which will yield in the country the best\nconditions, the best environment, the best system, the best results, the best\noutputs, the best outcomes for","logprobs":null,"stop_reason":null,"finish_reason":"length"}],"usage":{"prompt_tokens":7,"prompt_tokens_details":{"cached_tokens":0},"completion_tokens":132,"completion_tokens_details":{"reasoning_tokens":0},"total_tokens":139,"batch_size":[1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1],"queue_wait_time":[1024,965,627,1176,1169,783,1111,1054,1361,1186,980,765,1205,1774,1215,569,1151,695,706,594,877,1185,626,873,1016,201,575,851,1719,1085,985,1165,989,765,799,384,375,1004,1035,1127,307,816,883,1515,720,820,982,1472,898,1189,640,820,1200,630,2329,443,1010,692,908,1090,1019,1173,518,796,810,935,1498,1197,651,1243,1143,783,771,1108,667,473,1200,1112]}}
```
# CheckList
> PR提交人对以下CheckList自检项进行全量自检，自检通过或不涉及，均修改 [ ] 为 [x]。
- [x] 代码注释完备
- [x] 正确记录错误日志
- [x] 进行了返回值校验 (禁止使用void屏蔽安全函数、自研函数返回值；考虑接口的异常场景；调用底层组件接口时，需要进行返回值校验)
- [x] 进行了空指针校验
- [x] 若存在资源申请，使用后资源被正确的释放了
- [ ] 若涉及多线程场景，考虑了并发场景，不存在死锁问题
- [x] 按照[代码仓中提供的格式模板](https://gitcode.com/Ascend/MindIE-LLM/blob/master/.clang-format)，使用clang-format工具格式化代码
- [ ] 符合Ascend社区的编码规范。[C++ 语言编程指导](https://gitcode.com/Ascend/community/blob/master/docs/contributor/Ascend-cpp-coding-style-guide.md) | [C++ 语言安全编程指导](https://gitcode.com/Ascend/community/blob/master/docs/contributor/Ascend-cpp-secure-coding-guide.md)
See merge request: Ascend/MindIE-LLM!160
[新需求] 新增aclgraph独立工具类
Co-authored-by: Dawn952<zhaojunbo13@huawei.com>
# message auto-generated for no-merge-commit merge:
!160 merge independent_utils_and_files into dev
[新需求] 新增aclgraph独立工具类
Created-by: Dawn952
Commit-by: Dawn952
Merged-by: ascend-robot
Description: <!--
PR描述模板更新日期：20251225
-->
# 合入背景
> 补充aclgraph需要的工具文件。\
> 注意：Fixes #ISSUE ID会自动关闭issue，如问题部分解决请不要使用Fixes，可以用Fix part of #ISSUE ID替代.
Fix part of #103
# 修改内容
> 新增了hf.py 用于做huggingface相关校验；新增了url.py 用于屏蔽报错信息中的url信息； 新增了models.__init__ 作为model_runner调用的入口；
新增load_config.py 提供LoadConfig类型； 修改了huggingface_config.py 增加部分参数定义，增加校验。
# 资料变更
> 不涉及。
# 接口变更
> 不涉及。
# 测试结果
> 在aclgraph联调分支完成验证。\
- DeepSeek-V3.2-1201-w8a8 A3 16卡
```
curl -curl -H "Accept: application/json" -H "Content-type: application/json" -X POST -d '{
"model": "ds_v3.2",
"prompt": "What is the best model in China",
"stream": false,
"ignore_eos": false,
"max_tokens": 132
}' http://141.61.105.118:1025/v1/completions
{"id":"endpoint_common_1","object":"text_completion","created":1767753398,"model":"ds_v3.2","choices":[{"index":0,"text":"? In Taiwan? In New Zealand? In Canada? In\nJapan? In the United States? In Israel? In Singapore?\n\nSome of the answers to these questions have to be in the form of what the\nbest model of government and governance is in each country.\n\nThe best model is that one which will yield in the country the best\nconditions, the best environment, the best system, the best results, the best\noutputs, the best outcomes.\n\nThe best model is that one which will yield in the country the best\nconditions, the best environment, the best system, the best results, the best\noutputs, the best outcomes for","logprobs":null,"stop_reason":null,"finish_reason":"length"}],"usage":{"prompt_tokens":7,"prompt_tokens_details":{"cached_tokens":0},"completion_tokens":132,"completion_tokens_details":{"reasoning_tokens":0},"total_tokens":139,"batch_size":[1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1],"queue_wait_time":[1024,965,627,1176,1169,783,1111,1054,1361,1186,980,765,1205,1774,1215,569,1151,695,706,594,877,1185,626,873,1016,201,575,851,1719,1085,985,1165,989,765,799,384,375,1004,1035,1127,307,816,883,1515,720,820,982,1472,898,1189,640,820,1200,630,2329,443,1010,692,908,1090,1019,1173,518,796,810,935,1498,1197,651,1243,1143,783,771,1108,667,473,1200,1112]}}
```
# CheckList
> PR提交人对以下CheckList自检项进行全量自检，自检通过或不涉及，均修改 [ ] 为 [x]。
- [x] 代码注释完备
- [x] 正确记录错误日志
- [x] 进行了返回值校验 (禁止使用void屏蔽安全函数、自研函数返回值；考虑接口的异常场景；调用底层组件接口时，需要进行返回值校验)
- [x] 进行了空指针校验
- [x] 若存在资源申请，使用后资源被正确的释放了
- [ ] 若涉及多线程场景，考虑了并发场景，不存在死锁问题
- [x] 按照[代码仓中提供的格式模板](https://gitcode.com/Ascend/MindIE-LLM/blob/master/.clang-format)，使用clang-format工具格式化代码
- [ ] 符合Ascend社区的编码规范。[C++ 语言编程指导](https://gitcode.com/Ascend/community/blob/master/docs/contributor/Ascend-cpp-coding-style-guide.md) | [C++ 语言安全编程指导](https://gitcode.com/Ascend/community/blob/master/docs/contributor/Ascend-cpp-secure-coding-guide.md)
See merge request: Ascend/MindIE-LLM!160
