# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2025, vllm-ascend team
# This file is distributed under the same license as the vllm-ascend
# package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: vllm-ascend\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2025-07-18 09:01+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language-Team: zh_CN <LL@li.org>\n"
"Language: zh_CN\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Plural-Forms: nplurals=1; plural=0;\n"
"Generated-By: Babel 2.17.0\n"

#: ../../faqs.md:1
msgid "FAQs"
msgstr ""

#: ../../faqs.md:3
msgid "Version Specific FAQs"
msgstr "特定版本常见问题"

#: ../../faqs.md:5
msgid ""
"[[v0.7.3.post1] FAQ & Feedback](https://github.com/vllm-project/vllm-"
"ascend/issues/1007)"
msgstr ""
"[[v0.7.3.post1] 常见问题与反馈](https://github.com/vllm-project/vllm-"
"ascend/issues/1007)"

#: ../../faqs.md:6
msgid ""
"[[v0.9.2rc1] FAQ & Feedback](https://github.com/vllm-project/vllm-"
"ascend/issues/1742)"
msgstr ""
"[[v0.9.2rc1] 常见问题与反馈](https://github.com/vllm-project/vllm-"
"ascend/issues/1742)"

#: ../../faqs.md:8
msgid "General FAQs"
msgstr "常见问题解答"

#: ../../faqs.md:10
msgid "1. What devices are currently supported?"
msgstr "1. 目前支持哪些设备？"

#: ../../faqs.md:12
msgid ""
"Currently, **ONLY** Atlas A2 series(Ascend-cann-kernels-910b) and Atlas "
"300I(Ascend-cann-kernels-310p) series are supported:"
msgstr ""
"目前，**仅**支持 Atlas A2 系列（Ascend-cann-kernels-910b）和 Atlas 300I（Ascend-cann-"
"kernels-310p）系列："

#: ../../faqs.md:14
msgid ""
"Atlas A2 Training series (Atlas 800T A2, Atlas 900 A2 PoD, Atlas 200T A2 "
"Box16, Atlas 300T A2)"
msgstr ""
"Atlas A2 训练系列（Atlas 800T A2，Atlas 900 A2 PoD，Atlas 200T A2 Box16，Atlas 300T "
"A2）"

#: ../../faqs.md:15
msgid "Atlas 800I A2 Inference series (Atlas 800I A2)"
msgstr "Atlas 800I A2 推理系列（Atlas 800I A2）"

#: ../../faqs.md:16
msgid "Atlas 300I Inference series (Atlas 300I Duo)"
msgstr "Atlas 300I 推理系列（Atlas 300I Duo）"

#: ../../faqs.md:18
msgid "Below series are NOT supported yet:"
msgstr "以下系列目前尚不受支持："

#: ../../faqs.md:19
msgid "Atlas 200I A2 (Ascend-cann-kernels-310b) unplanned yet"
msgstr "Atlas 200I A2（Ascend-cann-kernels-310b）尚未计划"

#: ../../faqs.md:20
msgid "Ascend 910, Ascend 910 Pro B (Ascend-cann-kernels-910) unplanned yet"
msgstr "Ascend 910，Ascend 910 Pro B（Ascend-cann-kernels-910）尚未计划"

#: ../../faqs.md:22
msgid ""
"From a technical view, vllm-ascend support would be possible if the torch-"
"npu is supported. Otherwise, we have to implement it by using custom ops. We"
" are also welcome to join us to improve together."
msgstr ""
"从技术角度来看，如果支持 torch-npu，则可以支持 vllm-ascend。否则，我们需要通过自定义算子来实现。我们也欢迎大家一起加入，共同改进。"

#: ../../faqs.md:24
msgid "2. How to get our docker containers?"
msgstr "2. 如何获取我们的 docker 容器？"

#: ../../faqs.md:26
msgid ""
"You can get our containers at `Quay.io`, e.g., [<u>vllm-"
"ascend</u>](https://quay.io/repository/ascend/vllm-ascend?tab=tags) and "
"[<u>cann</u>](https://quay.io/repository/ascend/cann?tab=tags)."
msgstr ""
"你可以在 `Quay.io` 获取我们的容器，例如，[<u>vllm-"
"ascend</u>](https://quay.io/repository/ascend/vllm-ascend?tab=tags) 和 "
"[<u>cann</u>](https://quay.io/repository/ascend/cann?tab=tags)。"

#: ../../faqs.md:28
msgid ""
"If you are in China, you can use `daocloud` to accelerate your downloading:"
msgstr "如果你在中国，可以使用 `daocloud` 来加速下载："

#: ../../faqs.md:36
msgid "3. What models does vllm-ascend supports?"
msgstr "3. vllm-ascend 支持哪些模型？"

#: ../../faqs.md:38
msgid ""
"Find more details [<u>here</u>](https://vllm-"
"ascend.readthedocs.io/en/latest/user_guide/support_matrix/supported_models.html)."
msgstr ""
"在[<u>此处</u>](https://vllm-"
"ascend.readthedocs.io/en/latest/user_guide/support_matrix/supported_models.html)查看更多详细信息。"

#: ../../faqs.md:40
msgid "4. How to get in touch with our community?"
msgstr "4. 如何与我们的社区取得联系？"

#: ../../faqs.md:42
msgid ""
"There are many channels that you can communicate with our community "
"developers / users:"
msgstr "你可以通过多种渠道与我们的社区开发者/用户进行交流："

#: ../../faqs.md:44
msgid ""
"Submit a GitHub [<u>issue</u>](https://github.com/vllm-project/vllm-"
"ascend/issues?page=1)."
msgstr ""
"提交一个 GitHub [<u>issue</u>](https://github.com/vllm-project/vllm-"
"ascend/issues?page=1)。"

#: ../../faqs.md:45
msgid ""
"Join our [<u>weekly "
"meeting</u>](https://docs.google.com/document/d/1hCSzRTMZhIB8vRq1_qOOjx4c9uYUxvdQvDsMV2JcSrw/edit?tab=t.0#heading=h.911qu8j8h35z)"
" and share your ideas."
msgstr ""
"加入我们的[<u>每周会议</u>](https://docs.google.com/document/d/1hCSzRTMZhIB8vRq1_qOOjx4c9uYUxvdQvDsMV2JcSrw/edit?tab=t.0#heading=h.911qu8j8h35z)，并分享你的想法。"

#: ../../faqs.md:46
msgid ""
"Join our [<u>WeChat</u>](https://github.com/vllm-project/vllm-"
"ascend/issues/227) group and ask your quenstions."
msgstr ""
"加入我们的 [<u>微信群</u>](https://github.com/vllm-project/vllm-ascend/issues/227) "
"并提问你的问题。"

#: ../../faqs.md:47
msgid ""
"Join our ascend channel in [<u>vLLM "
"forums</u>](https://discuss.vllm.ai/c/hardware-support/vllm-ascend-"
"support/6) and publish your topics."
msgstr ""
"加入我们在 [<u>vLLM 论坛</u>](https://discuss.vllm.ai/c/hardware-support/vllm-"
"ascend-support/6) 的 ascend 频道并发布你的话题。"

#: ../../faqs.md:49
msgid "5. What features does vllm-ascend V1 supports?"
msgstr "5. vllm-ascend V1 支持哪些功能？"

#: ../../faqs.md:51
msgid ""
"Find more details [<u>here</u>](https://vllm-"
"ascend.readthedocs.io/en/latest/user_guide/support_matrix/supported_features.html)."
msgstr ""
"在[<u>这里</u>](https://vllm-"
"ascend.readthedocs.io/en/latest/user_guide/support_matrix/supported_features.html)找到更多详细信息。"

#: ../../faqs.md:53
msgid ""
"6. How to solve the problem of \"Failed to infer device type\" or "
"\"libatb.so: cannot open shared object file\"?"
msgstr "6. 如何解决“无法推断设备类型”或“libatb.so：无法打开共享对象文件”问题？"

#: ../../faqs.md:55
msgid ""
"Basically, the reason is that the NPU environment is not configured "
"correctly. You can:"
msgstr "基本上，原因是 NPU 环境没有正确配置。你可以："

#: ../../faqs.md:56
msgid ""
"try `source /usr/local/Ascend/nnal/atb/set_env.sh` to enable NNAL package."
msgstr "尝试运行 `source /usr/local/Ascend/nnal/atb/set_env.sh` 以启用 NNAL 包。"

#: ../../faqs.md:57
msgid ""
"try `source /usr/local/Ascend/ascend-toolkit/set_env.sh` to enable CANN "
"package."
msgstr "尝试运行 `source /usr/local/Ascend/ascend-toolkit/set_env.sh` 以启用 CANN 包。"

#: ../../faqs.md:58
msgid "try `npu-smi info` to check whether the NPU is working."
msgstr "尝试运行 `npu-smi info` 来检查 NPU 是否正常工作。"

#: ../../faqs.md:60
msgid ""
"If all above steps are not working, you can try the following code with "
"python to check whether there is any error:"
msgstr "如果以上所有步骤都无效，你可以尝试使用以下 python 代码来检查是否有错误："

#: ../../faqs.md:68
msgid ""
"If all above steps are not working, feel free to submit a GitHub issue."
msgstr "如果以上所有步骤都无法解决问题，欢迎提交一个 GitHub issue。"

#: ../../faqs.md:70
msgid "7. How does vllm-ascend perform?"
msgstr "7. vllm-ascend 的性能如何？"

#: ../../faqs.md:72
msgid ""
"Currently, only some models are improved. Such as `Qwen2.5 VL`, `Qwen3`, "
"`Deepseek  V3`. Others are not good enough. From 0.9.0rc2, Qwen and Deepseek"
" works with graph mode to play a good performance. What's more, you can "
"install `mindie-turbo` with `vllm-ascend v0.7.3` to speed up the inference "
"as well."
msgstr ""
"目前，只有部分模型得到了改进，比如 `Qwen2.5 VL`、`Qwen3` 和 `Deepseek V3`。其他模型的效果还不够理想。从 "
"0.9.0rc2 开始，Qwen 和 Deepseek 已经支持图模式，以获得更好的性能。此外，你还可以在 `vllm-ascend v0.7.3` "
"上安装 `mindie-turbo`，进一步加速推理。"

#: ../../faqs.md:74
msgid "8. How vllm-ascend work with vllm?"
msgstr "8. vllm-ascend 如何与 vllm 协同工作？"

#: ../../faqs.md:75
msgid ""
"vllm-ascend is a plugin for vllm. Basically, the version of vllm-ascend is "
"the same as the version of vllm. For example, if you use vllm 0.7.3, you "
"should use vllm-ascend 0.7.3 as well. For main branch, we will make sure "
"`vllm-ascend` and `vllm` are compatible by each commit."
msgstr ""
"vllm-ascend 是 vllm 的一个插件。基本上，vllm-ascend 的版本与 vllm 的版本是相同的。例如，如果你使用 vllm "
"0.7.3，你也应该使用 vllm-ascend 0.7.3。对于主分支，我们会确保每次提交都让 `vllm-ascend` 和 `vllm` "
"保持兼容。"

#: ../../faqs.md:77
msgid "9. Does vllm-ascend support Prefill Disaggregation feature?"
msgstr "9. vllm-ascend 支持 Prefill Disaggregation 功能吗？"

#: ../../faqs.md:79
msgid ""
"Currently, only 1P1D is supported on V0 Engine. For V1 Engine or NPND "
"support, We will make it stable and supported by vllm-ascend in the future."
msgstr "目前，V0引擎只支持1P1D。对于V1引擎或NPND的支持，我们将在未来使其稳定并由vllm-ascend支持。"

#: ../../faqs.md:81
msgid "10. Does vllm-ascend support quantization method?"
msgstr "10. vllm-ascend 支持量化方法吗？"

#: ../../faqs.md:83
msgid ""
"Currently, w8a8 quantization is already supported by vllm-ascend originally "
"on v0.8.4rc2 or higher, If you're using vllm 0.7.3 version, w8a8 "
"quantization is supporeted with the integration of vllm-ascend and mindie-"
"turbo, please use `pip install vllm-ascend[mindie-turbo]`."
msgstr ""
"目前，w8a8 量化已在 v0.8.4rc2 或更高版本的 vllm-ascend 中原生支持。如果你使用的是 vllm 0.7.3 版本，集成了 "
"vllm-ascend 和 mindie-turbo 后也支持 w8a8 量化，请使用 `pip install vllm-ascend[mindie-"
"turbo]`。"

#: ../../faqs.md:85
msgid "11. How to run w8a8 DeepSeek model?"
msgstr "11. 如何运行 w8a8 DeepSeek 模型？"

#: ../../faqs.md:87
msgid ""
"Please following the [inferencing tutorail](https://vllm-"
"ascend.readthedocs.io/en/latest/tutorials/multi_node.html) and replace model"
" to DeepSeek."
msgstr ""
"请按照[inferencing 教程](https://vllm-"
"ascend.readthedocs.io/en/latest/tutorials/multi_node.html)进行操作，并将模型更换为 "
"DeepSeek。"

#: ../../faqs.md:89
msgid ""
"12. There is no output in log when loading models using vllm-ascend, How to "
"solve it?"
msgstr "12. 使用 vllm-ascend 加载模型时日志没有输出，如何解决？"

#: ../../faqs.md:91
msgid ""
"If you're using vllm 0.7.3 version, this is a known progress bar display "
"issue in VLLM, which has been resolved in [this PR](https://github.com/vllm-"
"project/vllm/pull/12428), please cherry-pick it locally by yourself. "
"Otherwise, please fill up an issue."
msgstr ""
"如果你正在使用 vllm 0.7.3 版本，这是 VLLM 已知的进度条显示问题，已在 [此 PR](https://github.com/vllm-"
"project/vllm/pull/12428) 中解决，请自行在本地进行 cherry-pick。否则，请提交一个 issue。"

#: ../../faqs.md:93
msgid "13. How vllm-ascend is tested"
msgstr "13. 如何测试 vllm-ascend"

#: ../../faqs.md:95
msgid ""
"vllm-ascend is tested by functional test, performance test and accuracy "
"test."
msgstr "vllm-ascend 经过功能测试、性能测试和精度测试。"

#: ../../faqs.md:97
msgid ""
"**Functional test**: we added CI, includes portion of vllm's native unit "
"tests and vllm-ascend's own unit tests，on vllm-ascend's test, we test basic "
"functionality、popular models availability and [supported "
"features](https://vllm-"
"ascend.readthedocs.io/en/latest/user_guide/support_matrix/supported_features.html)"
" via e2e test"
msgstr ""
"**功能测试**：我们添加了CI，包含了vllm原生单元测试的一部分以及vllm-ascend自己的单元测试。在vllm-"
"ascend的测试中，我们通过e2e测试验证了基本功能、主流模型可用性和[支持的特性](https://vllm-"
"ascend.readthedocs.io/en/latest/user_guide/support_matrix/supported_features.html)。"

#: ../../faqs.md:99
msgid ""
"**Performance test**: we provide [benchmark](https://github.com/vllm-"
"project/vllm-ascend/tree/main/benchmarks) tools for end-to-end performance "
"benchmark which can easily to re-route locally, we'll publish a perf website"
" to show the performance test results for each pull request"
msgstr ""
"**性能测试**：我们提供了用于端到端性能基准测试的[基准测试](https://github.com/vllm-project/vllm-"
"ascend/tree/main/benchmarks)工具，可以方便地在本地重新运行。我们将发布一个性能网站，用于展示每个拉取请求的性能测试结果。"

#: ../../faqs.md:101
msgid ""
"**Accuracy test**: we're working on adding accuracy test to CI as well."
msgstr "**准确性测试**：我们也在努力将准确性测试添加到CI中。"

#: ../../faqs.md:103
msgid ""
"Finnall, for each release, we'll publish the performance test and accuracy "
"test report in the future."
msgstr "最后，未来每个版本发布时，我们都会公开性能测试和准确性测试报告。"

#: ../../faqs.md:105
msgid "14. How to fix the error \"InvalidVersion\" when using vllm-ascend?"
msgstr "14. 使用 vllm-ascend 时如何解决 “InvalidVersion” 错误？"

#: ../../faqs.md:106
msgid ""
"It's usually because you have installed an dev/editable version of vLLM "
"package. In this case, we provide the env variable `VLLM_VERSION` to let "
"users specify the version of vLLM package to use. Please set the env "
"variable `VLLM_VERSION` to the version of vLLM package you have installed. "
"The format of `VLLM_VERSION` should be `X.Y.Z`."
msgstr ""
"这通常是因为你安装了开发版或可编辑版本的 vLLM 包。在这种情况下，我们提供了环境变量 `VLLM_VERSION`，以便用户指定要使用的 vLLM "
"包版本。请将环境变量 `VLLM_VERSION` 设置为你已安装的 vLLM 包的版本。`VLLM_VERSION` 的格式应为 `X.Y.Z`。"

#: ../../faqs.md:108
msgid "15. How to handle Out Of Memory?"
msgstr "15. 如何处理内存溢出？"

#: ../../faqs.md:109
msgid ""
"OOM errors typically occur when the model exceeds the memory capacity of a "
"single NPU. For general guidance, you can refer to [vLLM's OOM "
"troubleshooting "
"documentation](https://docs.vllm.ai/en/latest/getting_started/troubleshooting.html#out-"
"of-memory)."
msgstr ""
"当模型超出单个 NPU 的内存容量时，通常会发生 OOM（内存溢出）错误。一般性的指导可以参考 [vLLM 的 OOM "
"故障排除文档](https://docs.vllm.ai/en/latest/getting_started/troubleshooting.html#out-"
"of-memory)。"

#: ../../faqs.md:111
msgid ""
"In scenarios where NPUs have limited HBM (High Bandwidth Memory) capacity, "
"dynamic memory allocation/deallocation during inference can exacerbate "
"memory fragmentation, leading to OOM. To address this:"
msgstr ""
"在 NPU 的 HBM（高带宽内存）容量有限的场景下，推理过程中动态内存分配和释放会加剧内存碎片，从而导致 OOM（内存溢出）。为了解决这个问题："

#: ../../faqs.md:113
msgid ""
"**Adjust `--gpu-memory-utilization`**: If unspecified, will use the default "
"value of `0.9`. You can decrease this param to reserve more memory to reduce"
" fragmentation risks. See more note in: [vLLM - Inference and Serving - "
"Engine "
"Arguments](https://docs.vllm.ai/en/latest/serving/engine_args.html#vllm.engine.arg_utils-"
"_engine_args_parser-cacheconfig)."
msgstr ""
"**调整 `--gpu-memory-utilization`**：如果未指定，将使用默认值 "
"`0.9`。你可以降低此参数来预留更多内存，从而降低内存碎片风险。参见更多说明：[vLLM - 推理与服务 - "
"引擎参数](https://docs.vllm.ai/en/latest/serving/engine_args.html#vllm.engine.arg_utils-"
"_engine_args_parser-cacheconfig)。"

#: ../../faqs.md:115
msgid ""
"**Configure `PYTORCH_NPU_ALLOC_CONF`**: Set this environment variable to "
"optimize NPU memory management. For example, you can `export "
"PYTORCH_NPU_ALLOC_CONF=expandable_segments:True` to enable virtual memory "
"feature to mitigate memory fragmentation caused by frequent dynamic memory "
"size adjustments during runtime, see more note in: "
"[PYTORCH_NPU_ALLOC_CONF](https://www.hiascend.com/document/detail/zh/Pytorch/700/comref/Envvariables/Envir_012.html)."
msgstr ""
"**配置 `PYTORCH_NPU_ALLOC_CONF`**：设置此环境变量以优化NPU内存管理。例如，你可以通过 `export "
"PYTORCH_NPU_ALLOC_CONF=expandable_segments:True` "
"来启用虚拟内存功能，以缓解运行时频繁动态调整内存大小导致的内存碎片问题，更多说明参见：[PYTORCH_NPU_ALLOC_CONF](https://www.hiascend.com/document/detail/zh/Pytorch/700/comref/Envvariables/Envir_012.html)。"

#: ../../faqs.md:117
msgid "16. Failed to enable NPU graph mode when running DeepSeek?"
msgstr "16. 运行 DeepSeek 时无法启用 NPU 图模式？"

#: ../../faqs.md:118
#, python-brace-format
msgid ""
"You may encounter the following error if running DeepSeek with NPU graph "
"mode enabled. The allowed number of queries per kv when enabling both MLA "
"and Graph mode only support {32, 64, 128}, **Thus this is not supported for "
"DeepSeek-V2-Lite**, as it only has 16 attention heads. The NPU graph mode "
"support on DeepSeek-V2-Lite will be done in the future."
msgstr ""
"如果在启用NPU图模式（Graph "
"mode）运行DeepSeek时，您可能会遇到以下错误。当同时启用MLA和图模式时，每个kv允许的查询数只支持{32, 64, "
"128}，**因此这不支持DeepSeek-V2-Lite**，因为它只有16个注意力头。未来会增加对DeepSeek-V2-Lite在NPU图模式下的支持。"

#: ../../faqs.md:120
#, python-brace-format
msgid ""
"And if you're using DeepSeek-V3 or DeepSeek-R1, please make sure after the "
"tensor parallel split, num_heads / num_kv_heads in {32, 64, 128}."
msgstr ""
"如果你正在使用 DeepSeek-V3 或 DeepSeek-R1，请确保在张量并行切分后，num_heads / num_kv_heads 的值为 "
"{32, 64, 128} 中的一个。"

#: ../../faqs.md:127
msgid ""
"17. Failed to reinstall vllm-ascend from source after uninstalling vllm-"
"ascend?"
msgstr "17. 卸载 vllm-ascend 后无法从源码重新安装 vllm-ascend？"

#: ../../faqs.md:128
msgid ""
"You may encounter the problem of C compilation failure when reinstalling "
"vllm-ascend from source using pip. If the installation fails, it is "
"recommended to use `python setup.py install` to install, or use `python "
"setup.py clean` to clear the cache."
msgstr ""
"当你使用 pip 从源码重新安装 vllm-ascend 时，可能会遇到 C 编译失败的问题。如果安装失败，建议使用 `python setup.py "
"install` 进行安装，或者使用 `python setup.py clean` 清除缓存。"

#: ../../faqs.md:130
msgid "18. How to generate determinitic results when using vllm-ascend?"
msgstr "18. 使用 vllm-ascend 时如何生成确定性结果？"

#: ../../faqs.md:131
msgid "There are several factors that affect output certainty:"
msgstr "有几个因素会影响输出的确定性："

#: ../../faqs.md:133
msgid ""
"Sampler Method: using **Greedy sample** by setting `temperature=0` in "
"`SamplingParams`, e.g.:"
msgstr ""
"采样方法：通过在 `SamplingParams` 中设置 `temperature=0` 来使用 **贪婪采样（Greedy "
"sample）**，例如："

#: ../../faqs.md:158
msgid "Set the following enveriments parameters:"
msgstr "设置以下环境参数："