| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
compilation合入 Co-authored-by: LostFox11<wangziyue17@huawei.com> # message auto-generated for no-merge-commit merge: !209 merge compliation into dev compilation合入 Created-by: LostFox11 Commit-by: LostFox11 Merged-by: ascend-robot Description: <!-- PR描述模板更新日期:20251225 --> # 合入背景 > Fix part of #103 # 修改内容 > 添加acl_graph_wrapper.py文件 当走aclgraph且decode情况下,在原来的model上包一层acl_graph_wrapper 其中包括实际选图、图的capture、replay、update等操作 # 资料变更 > 不涉及 # 接口变更 > 不涉及 # 测试结果 > 在A3机器上测试功能、性能、精度无误 # 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 - [ ] 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!209 | 6 个月前 | |
修复dp负载不均时计算kv_len和q_len的问题 Co-authored-by: earthmanylf<yulinfeng2@huawei.com> # message auto-generated for no-merge-commit merge: !879 merge spec into dev 修复dp负载不均时计算kv_len和q_len的问题 Created-by: earthmanylf Commit-by: earthmanylf Merged-by: ascend-robot Description: <!-- PR描述模板更新日期:20251225 --> # 合入背景 > 请描述为什么要做这个PR内的改动。\ > 如涉及,请关联前序PR或同特性/需求下的其他PR。\ > 如果是修复之前PR引入的问题,请关联引入问题的PR。\ > 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](https://gitcode.com/Ascend/MindIE-LLM/issues/103) # 修改内容 > 请描述修改内容的具体实现,涉及哪些组件之间进行交互,可以用1、2、3、...进行罗列。\ > 如果是需求或者重构类的PR,需要补充详细设计文档(说明上下游组件关系、时序图、类图、DFX能力等内容)。 修复dp负载不均时计算kv_len和q_len的问题 # 资料变更 > 请确认是否涉及资料变更。如涉及,需要在PR中体现,并简要说明修改内容。如不涉及,需填写“不涉及”。 不涉及 # 接口变更 > 请确认是否涉及跨代码仓或者客户面可见的接口变更。如涉及,需要详细说明接口以及对应的变更内容,同时需要在资料中体现。如不涉及,需填写“不涉及”。 不涉及 # 测试结果 > 请说明测试场景,测试方法以及测试结果。\ > 测试用例设计时需考虑硬件、部署方式、功能、性能、精度、显存等维度。 curl通: curl http://141.61.81.21:3025/v1/chat/completions -X POST -d'{"model": "ds","messages": [{"role": "user","content": "You are a helpful assistant."}],"stream": true,"temperature": 0,"max_tokens": 10}' data: {"id":"endpoint_common_0","object":"chat.completion.chunk","created":1776348349,"model":"ds","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]} data: {"id":"endpoint_common_0","object":"chat.completion.chunk","created":1776348349,"model":"ds","choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"logprobs":null,"finish_reason":null}]} data: {"id":"endpoint_common_0","object":"chat.completion.chunk","created":1776348349,"model":"ds","choices":[{"index":0,"delta":{"role":"assistant","content":"! I'm"},"logprobs":null,"finish_reason":null}]} data: {"id":"endpoint_common_0","object":"chat.completion.chunk","created":1776348349,"model":"ds","choices":[{"index":0,"delta":{"role":"assistant","content":" here to help"},"logprobs":null,"finish_reason":null}]} data: {"id":"endpoint_common_0","object":"chat.completion.chunk","created":1776348349,"model":"ds","choices":[{"index":0,"delta":{"role":"assistant","content":" you"},"logprobs":null,"finish_reason":null}]} data: {"id":"endpoint_common_0","object":"chat.completion.chunk","created":1776348349,"model":"ds","choices":[{"index":0,"delta":{"role":"assistant","content":"."},"logprobs":null,"finish_reason":null}]} data: {"id":"endpoint_common_0","object":"chat.completion.chunk","created":1776348349,"model":"ds","usage":{"prompt_tokens":10,"prompt_tokens_details":{"cached_tokens":0},"completion_tokens":10,"completion_tokens_details":{"reasoning_tokens":0},"total_tokens":20},"choices":[{"index":0,"delta":{"role":"assistant","content":" Whether"},"logprobs":null,"finish_reason":"length"}]} # 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 - [x] 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 - [x] 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!879 | 3 个月前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 6 个月前 | ||
| 3 个月前 |