提交vllm0.11.0开发分支
This commit is contained in:
chenyili
@@ -0,0 +1,245 @@
|
||||
# SOME DESCRIPTIVE TITLE.
|
||||
# Copyright (C) 2025, vllm-kunlun team
|
||||
# This file is distributed under the same license as the vllm-kunlun
|
||||
# package.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: vllm-kunlun\n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2025-11-10 16:59+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language: zh_CN\n"
|
||||
"Language-Team: zh_CN <LL@li.org>\n"
|
||||
"Plural-Forms: nplurals=1; plural=0;\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/configuration/additional_config.md:1
|
||||
msgid "Additional Configuration"
|
||||
msgstr "附加配置"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "additional configuration is a mechanism "
|
||||
#~ "provided by vLLM to allow plugins "
|
||||
#~ "to control inner behavior by their "
|
||||
#~ "own. vLLM Kunlun uses this mechanism "
|
||||
#~ "to make the project more flexible."
|
||||
#~ msgstr "额外配置是 vLLM 提供的一种机制，允许插件自行控制内部行为。vLLM Kunlun 利用这种机制使项目更加灵活。"
|
||||
|
||||
#~ msgid "How to use"
|
||||
#~ msgstr "如何使用"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "With either online mode or offline "
|
||||
#~ "mode, users can use additional "
|
||||
#~ "configuration. Take Qwen3 as an example:"
|
||||
#~ msgstr "无论是在线模式还是离线模式，用户都可以使用额外的配置。以 Qwen3 为例："
|
||||
|
||||
#~ msgid "**Online mode**:"
|
||||
#~ msgstr "**在线模式**："
|
||||
|
||||
#~ msgid "**Offline mode**:"
|
||||
#~ msgstr "**离线模式**："
|
||||
|
||||
#~ msgid "Configuration options"
|
||||
#~ msgstr "配置选项"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "The following table lists the additional"
|
||||
#~ " configuration options available in vLLM"
|
||||
#~ " Kunlun:"
|
||||
#~ msgstr "下表列出了 vLLM Kunlun 中可用的其他配置选项："
|
||||
|
||||
#~ msgid "Name"
|
||||
#~ msgstr "名称"
|
||||
|
||||
#~ msgid "Type"
|
||||
#~ msgstr "类型"
|
||||
|
||||
#~ msgid "Default"
|
||||
#~ msgstr "默认"
|
||||
|
||||
#~ msgid "Description"
|
||||
#~ msgstr "描述"
|
||||
|
||||
#~ msgid "`torchair_graph_config`"
|
||||
#~ msgstr "`torchair_graph_config`"
|
||||
|
||||
#~ msgid "dict"
|
||||
#~ msgstr "dict"
|
||||
|
||||
#~ msgid "`{}`"
|
||||
#~ msgstr "`{}`"
|
||||
|
||||
#~ msgid "The config options for torchair graph mode"
|
||||
#~ msgstr "torchair 图模式的配置选项"
|
||||
|
||||
#~ msgid "`kunlun_scheduler_config`"
|
||||
#~ msgstr "`kunlun_scheduler_config`"
|
||||
|
||||
#~ msgid "The config options for kunlun scheduler"
|
||||
#~ msgstr "kunlun 调度器的配置选项"
|
||||
|
||||
#~ msgid "`expert_tensor_parallel_size`"
|
||||
#~ msgstr "`expert_tensor_parallel_size`"
|
||||
|
||||
#~ msgid "str"
|
||||
#~ msgstr "str"
|
||||
|
||||
#~ msgid "`0`"
|
||||
#~ msgstr "`0`"
|
||||
|
||||
#~ msgid "Expert tensor parallel size the model to use."
|
||||
#~ msgstr "专家张量并行的模型大小设置。"
|
||||
|
||||
#~ msgid "`refresh`"
|
||||
#~ msgstr "`刷新`"
|
||||
|
||||
#~ msgid "bool"
|
||||
#~ msgstr "bool"
|
||||
|
||||
#~ msgid "`false`"
|
||||
#~ msgstr "`false`"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Whether to refresh global kunlun config"
|
||||
#~ " content. This value is usually used"
|
||||
#~ " by rlhf or ut/e2e test case."
|
||||
#~ msgstr "是否刷新全局 kunlun 配置信息。此值通常由 rlhf 或 ut/e2e 测试用例使用。"
|
||||
|
||||
#~ msgid "`expert_map_path`"
|
||||
#~ msgstr "`expert_map_path`"
|
||||
|
||||
#~ msgid "`None`"
|
||||
#~ msgstr "`None`"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "When using expert load balancing for "
|
||||
#~ "the MOE model, an expert map path"
|
||||
#~ " needs to be passed in."
|
||||
#~ msgstr "在为MOE模型使用专家负载均衡时，需要传入专家映射路径。"
|
||||
|
||||
#~ msgid "`False`"
|
||||
#~ msgstr "`False`"
|
||||
|
||||
#~ msgid "Whether to enable the fused operator-like chunked_prefill."
|
||||
#~ msgstr "是否启用类似算子融合的 chunked_prefill 功能。"
|
||||
|
||||
#~ msgid "`kv_cache_dtype`"
|
||||
#~ msgstr "`kv_cache_dtype`"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "When using the kv cache quantization "
|
||||
#~ "method, kv cache dtype needs to be"
|
||||
#~ " set, currently only int8 is "
|
||||
#~ "supported."
|
||||
#~ msgstr "当使用kv缓存量化方法时，需要设置kv缓存的数据类型，目前仅支持int8。"
|
||||
|
||||
#~ msgid "The details of each config option are as follows:"
|
||||
#~ msgstr "每个配置选项的详细信息如下："
|
||||
|
||||
#~ msgid "**torchair_graph_config**"
|
||||
#~ msgstr "**torchair_graph_config**"
|
||||
|
||||
#~ msgid "`enabled`"
|
||||
#~ msgstr "`启用`"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Whether to enable torchair graph mode."
|
||||
#~ " Currently only DeepSeek series models "
|
||||
#~ "and PanguProMoE are supported to use "
|
||||
#~ "torchair graph mode"
|
||||
#~ msgstr "是否启用 torchair 图模式。目前仅支持 DeepSeek 系列模型和 PanguProMoE 使用 torchair 图模式。"
|
||||
|
||||
#~ msgid "`enable_multistream_mla`"
|
||||
#~ msgstr "`enable_multistream_mla`"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Whether to put vector ops of MLA"
|
||||
#~ " to another stream. This option only"
|
||||
#~ " takes effects on models using MLA"
|
||||
#~ " (e.g., DeepSeek)."
|
||||
#~ msgstr "是否将MLA的向量操作放到另一个流中。此选项仅对使用MLA的模型（例如，DeepSeek）有效。"
|
||||
|
||||
#~ msgid "`multistream_overlap_shared_expert`"
|
||||
#~ msgstr "`multistream_overlap_shared_expert`"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Whether to enable multistream shared "
|
||||
#~ "expert. This option only takes effects"
|
||||
#~ " on DeepSeek moe models."
|
||||
#~ msgstr "是否启用多流共享专家功能。此选项仅对 DeepSeek MoE 模型生效。"
|
||||
|
||||
#~ msgid "`enable_view_optimize`"
|
||||
#~ msgstr "`enable_view_optimize` （启用视图优化）"
|
||||
|
||||
#~ msgid "`True`"
|
||||
#~ msgstr "`True`"
|
||||
|
||||
#~ msgid "Whether to enable torchair view optimization"
|
||||
#~ msgstr "是否启用torchair视图优化"
|
||||
|
||||
#~ msgid "`use_cached_graph`"
|
||||
#~ msgstr "`use_cached_graph`"
|
||||
|
||||
#~ msgid "Whether to use cached graph"
|
||||
#~ msgstr "是否使用缓存的图"
|
||||
|
||||
#~ msgid "`graph_batch_sizes`"
|
||||
#~ msgstr "`graph_batch_sizes`"
|
||||
|
||||
#~ msgid "list[int]"
|
||||
#~ msgstr "list[int]"
|
||||
|
||||
#~ msgid "`[]`"
|
||||
#~ msgstr "`[]`"
|
||||
|
||||
#~ msgid "The batch size for torchair graph cache"
|
||||
#~ msgstr "torchair 图缓存的批量大小"
|
||||
|
||||
#~ msgid "`graph_batch_sizes_init`"
|
||||
#~ msgstr "`graph_batch_sizes_init`"
|
||||
|
||||
#~ msgid "Init graph batch size dynamically if `graph_batch_sizes` is empty"
|
||||
#~ msgstr "如果 `graph_batch_sizes` 为空，则动态初始化图批大小"
|
||||
|
||||
#~ msgid "`enable_kv_nz`"
|
||||
#~ msgstr "`enable_kv_nz`"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Whether to enable kvcache NZ layout. "
|
||||
#~ "This option only takes effects on "
|
||||
#~ "models using MLA (e.g., DeepSeek)."
|
||||
#~ msgstr "是否启用 kvcache NZ 布局。此选项仅对使用 MLA 的模型（例如 DeepSeek）生效。"
|
||||
|
||||
#~ msgid "**kunlun_scheduler_config**"
|
||||
#~ msgstr "**kunlun_scheduler_config**"
|
||||
|
||||
#~ msgid "Whether to enable kunlun scheduler for V1 engine"
|
||||
#~ msgstr "是否为 V1 引擎启用 kunlun 调度器"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "kunlun_scheduler_config also support the "
|
||||
#~ "options from [vllm scheduler "
|
||||
#~ "config](https://docs.vllm.ai/en/stable/api/vllm/config.html#vllm.config.SchedulerConfig)."
|
||||
#~ " For example, you can add "
|
||||
#~ "`enable_chunked_prefill: True` to "
|
||||
#~ "kunlun_scheduler_config as well."
|
||||
#~ msgstr ""
|
||||
#~ "kunlun_scheduler_config 也支持来自 [vllm scheduler "
|
||||
#~ "config](https://docs.vllm.ai/en/stable/api/vllm/config.html#vllm.config.SchedulerConfig)"
|
||||
#~ " 的选项。例如，你也可以在 kunlun_scheduler_config 中添加 "
|
||||
#~ "`enable_chunked_prefill: True`。"
|
||||
|
||||
#~ msgid "Example"
|
||||
#~ msgstr "示例"
|
||||
|
||||
#~ msgid "An example of additional configuration is as follows:"
|
||||
#~ msgstr "以下是额外配置的一个示例："
|
||||
|
||||
@@ -0,0 +1,29 @@
|
||||
# Translations template for PROJECT.
|
||||
# Copyright (C) 2025 ORGANIZATION
|
||||
# This file is distributed under the same license as the PROJECT project.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: PROJECT VERSION\n"
|
||||
"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n"
|
||||
"POT-Creation-Date: 2025-11-10 16:59+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language-Team: LANGUAGE <LL@li.org>\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/configuration/env_vars.md:1
|
||||
msgid "Environment Variables"
|
||||
msgstr "环境变量"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "vllm-kunlun uses the following "
|
||||
#~ "environment variables to configure the "
|
||||
#~ "system:"
|
||||
#~ msgstr "vllm-kunlun 使用以下环境变量来配置系统："
|
||||
|
||||
@@ -0,0 +1,32 @@
|
||||
# SOME DESCRIPTIVE TITLE.
|
||||
# Copyright (C) 2025, vllm-kunlun team
|
||||
# This file is distributed under the same license as the vllm-kunlun
|
||||
# package.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: vllm-kunlun\n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2025-11-10 19:12+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language: zh_CN\n"
|
||||
"Language-Team: zh_CN <LL@li.org>\n"
|
||||
"Plural-Forms: nplurals=1; plural=0;\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/configuration/index.md:1
|
||||
#: ../../source/user_guide/configuration/index.md:5
|
||||
msgid "Configuration Guide"
|
||||
msgstr "配置指南"
|
||||
|
||||
#: ../../source/user_guide/configuration/index.md:3
|
||||
#, fuzzy
|
||||
msgid "This section provides a detailed configuration guide of vLLM Kunlun."
|
||||
msgstr "本节提供了 vLLM Kunlun 的详细配置指南。"
|
||||
|
||||
@@ -0,0 +1,26 @@
|
||||
# SOME DESCRIPTIVE TITLE.
|
||||
# Copyright (C) 2025, vllm-kunlun team
|
||||
# This file is distributed under the same license as the vllm-kunlun
|
||||
# package.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: vllm-kunlun \n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2025-11-10 16:59+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language: zh_CN\n"
|
||||
"Language-Team: zh_CN <LL@li.org>\n"
|
||||
"Plural-Forms: nplurals=1; plural=0;\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/dynamic_batch.md:1
|
||||
msgid "Dynamic Batch"
|
||||
msgstr ""
|
||||
|
||||
@@ -0,0 +1,30 @@
|
||||
# SOME DESCRIPTIVE TITLE.
|
||||
# Copyright (C) 2025, vllm-kunlun team
|
||||
# This file is distributed under the same license as the vllm-kunlun
|
||||
# package.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: vllm-kunlun \n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2025-11-10 16:59+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language: zh_CN\n"
|
||||
"Language-Team: zh_CN <LL@li.org>\n"
|
||||
"Plural-Forms: nplurals=1; plural=0;\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/eplb_swift_balancer.md:1
|
||||
msgid "Expert Load Balance (EPLB)"
|
||||
msgstr ""
|
||||
|
||||
#: ../../source/user_guide/feature_guide/eplb_swift_balancer.md:3
|
||||
msgid "Overview"
|
||||
msgstr ""
|
||||
|
||||
@@ -0,0 +1,126 @@
|
||||
# Translations template for PROJECT.
|
||||
# Copyright (C) 2025 ORGANIZATION
|
||||
# This file is distributed under the same license as the PROJECT project.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: PROJECT VERSION\n"
|
||||
"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n"
|
||||
"POT-Creation-Date: 2025-11-10 16:59+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language-Team: LANGUAGE <LL@li.org>\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/graph_mode.md:1
|
||||
msgid "Graph Mode Guide"
|
||||
msgstr "图模式指南"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "This feature is currently experimental. "
|
||||
#~ "In future versions, there may be "
|
||||
#~ "behavioral changes around configuration, "
|
||||
#~ "coverage, performance improvement."
|
||||
#~ msgstr "此功能目前为实验性功能。在未来的版本中，配置、覆盖率和性能改进等方面的行为可能会有变化。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "This guide provides instructions for "
|
||||
#~ "using Kunlun Graph Mode with vLLM "
|
||||
#~ "Kunlun. Please note that graph mode "
|
||||
#~ "is only available on V1 Engine. "
|
||||
#~ "And only Qwen, DeepSeek series models"
|
||||
#~ " are well tested from 0.9.0rc1. We'll"
|
||||
#~ " make it stable and generalize in "
|
||||
#~ "the next release."
|
||||
#~ msgstr ""
|
||||
#~ "本指南提供了在 vLLM Kunlun 上使用 Kunlun "
|
||||
#~ "图模式的操作说明。请注意，图模式仅在 V1 引擎上可用，并且从 0.9.0rc1 起，仅对"
|
||||
#~ " Qwen、DeepSeek 系列模型进行了充分测试。我们将在下一个版本中使其更加稳定和通用。"
|
||||
|
||||
#~ msgid "Getting Started"
|
||||
#~ msgstr "快速入门"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "From v0.9.1rc1 with V1 Engine, vLLM "
|
||||
#~ "Kunlun will run models in graph "
|
||||
#~ "mode by default to keep the same"
|
||||
#~ " behavior with vLLM. If you hit "
|
||||
#~ "any issues, please feel free to "
|
||||
#~ "open an issue on GitHub and "
|
||||
#~ "fallback to eager mode temporarily by"
|
||||
#~ " set `enforce_eager=True` when initializing "
|
||||
#~ "the model."
|
||||
#~ msgstr ""
|
||||
#~ "从 v0.9.1rc1 版本起，使用 V1 引擎时，vLLM Kunlun"
|
||||
#~ " 默认将在图模式下运行模型，以保持与 vLLM 同样的行为。如果遇到任何问题，欢迎在 GitHub"
|
||||
#~ " 上提交 issue，并在初始化模型时通过设置 `enforce_eager=True` "
|
||||
#~ "临时切换回 eager 模式。"
|
||||
|
||||
#~ msgid "There are two kinds for graph mode supported by vLLM Kunlun:"
|
||||
#~ msgstr "vLLM Kunlun 支持两种图模式："
|
||||
|
||||
#~ msgid ""
|
||||
#~ "**ACLGraph**: This is the default graph"
|
||||
#~ " mode supported by vLLM Kunlun. In"
|
||||
#~ " v0.9.1rc1, only Qwen series models "
|
||||
#~ "are well tested."
|
||||
#~ msgstr ""
|
||||
#~ "**ACLGraph**：这是 vLLM Kunlun 支持的默认图模式。在 "
|
||||
#~ "v0.9.1rc1 版本中，只有 Qwen 系列模型得到了充分测试。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "**TorchAirGraph**: This is the GE graph"
|
||||
#~ " mode. In v0.9.1rc1, only DeepSeek "
|
||||
#~ "series models are supported."
|
||||
#~ msgstr "**TorchAirGraph**：这是GE图模式。在v0.9.1rc1版本中，仅支持DeepSeek系列模型。"
|
||||
|
||||
#~ msgid "Using ACLGraph"
|
||||
#~ msgstr "使用 ACLGraph"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "ACLGraph is enabled by default. Take "
|
||||
#~ "Qwen series models as an example, "
|
||||
#~ "just set to use V1 Engine is "
|
||||
#~ "enough."
|
||||
#~ msgstr "ACLGraph 默认启用。以 Qwen 系列模型为例，只需设置为使用 V1 引擎即可。"
|
||||
|
||||
#~ msgid "offline example:"
|
||||
#~ msgstr "离线示例："
|
||||
|
||||
#~ msgid "online example:"
|
||||
#~ msgstr "在线示例："
|
||||
|
||||
#~ msgid "Using TorchAirGraph"
|
||||
#~ msgstr "使用 TorchAirGraph"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "If you want to run DeepSeek series"
|
||||
#~ " models with graph mode, you should"
|
||||
#~ " use "
|
||||
#~ "[TorchAirGraph](https://www.hikunlun.com/document/detail/zh/Pytorch/700/modthirdparty/torchairuseguide/torchair_0002.html)."
|
||||
#~ " In this case, additional config is"
|
||||
#~ " required."
|
||||
#~ msgstr ""
|
||||
#~ "如果你想通过图模式运行 DeepSeek 系列模型，你应该使用 "
|
||||
#~ "[TorchAirGraph](https://www.hikunlun.com/document/detail/zh/Pytorch/700/modthirdparty/torchairuseguide/torchair_0002.html)。在这种情况下，需要额外的配置。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "You can find more detail about "
|
||||
#~ "additional config "
|
||||
#~ "[here](../configuration/additional_config.md)."
|
||||
#~ msgstr "你可以在[这里](../configuration/additional_config.md)找到关于附加配置的更多详细信息。"
|
||||
|
||||
#~ msgid "Fallback to Eager Mode"
|
||||
#~ msgstr "回退到 Eager 模式"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "If both `ACLGraph` and `TorchAirGraph` "
|
||||
#~ "fail to run, you should fallback "
|
||||
#~ "to eager mode."
|
||||
#~ msgstr "如果 `ACLGraph` 和 `TorchAirGraph` 都无法运行，你应该退回到 eager 模式。"
|
||||
|
||||
@@ -0,0 +1,32 @@
|
||||
# SOME DESCRIPTIVE TITLE.
|
||||
# Copyright (C) 2025, vllm-kunlun team
|
||||
# This file is distributed under the same license as the vllm-kunlun
|
||||
# package.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: vllm-kunlun\n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2025-11-10 19:12+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language: zh_CN\n"
|
||||
"Language-Team: zh_CN <LL@li.org>\n"
|
||||
"Plural-Forms: nplurals=1; plural=0;\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/index.md:1
|
||||
#: ../../source/user_guide/feature_guide/index.md:5
|
||||
msgid "Feature Guide"
|
||||
msgstr "功能指南"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/index.md:3
|
||||
#, fuzzy
|
||||
msgid "This section provides a detailed usage guide of vLLM Kunlun features."
|
||||
msgstr "本节提供了 vLLM Kunlun 功能的详细使用指南。"
|
||||
|
||||
@@ -0,0 +1,30 @@
|
||||
# SOME DESCRIPTIVE TITLE.
|
||||
# Copyright (C) 2025, vllm-kunlun team
|
||||
# This file is distributed under the same license as the vllm-kunlun
|
||||
# package.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: vllm-kunlun \n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2025-11-10 16:59+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language: zh_CN\n"
|
||||
"Language-Team: zh_CN <LL@li.org>\n"
|
||||
"Plural-Forms: nplurals=1; plural=0;\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/kv_pool_mooncake.md:1
|
||||
msgid "Mooncacke Store Deployment Guide"
|
||||
msgstr ""
|
||||
|
||||
#: ../../source/user_guide/feature_guide/kv_pool_mooncake.md:3
|
||||
msgid "Environmental Dependencies"
|
||||
msgstr ""
|
||||
|
||||
@@ -0,0 +1,68 @@
|
||||
# SOME DESCRIPTIVE TITLE.
|
||||
# Copyright (C) 2025, vllm-kunlun team
|
||||
# This file is distributed under the same license as the vllm-kunlun
|
||||
# package.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: vllm-kunlun\n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2025-11-10 16:59+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language: zh_CN\n"
|
||||
"Language-Team: zh_CN <LL@li.org>\n"
|
||||
"Plural-Forms: nplurals=1; plural=0;\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/lora.md:1
|
||||
msgid "LoRA Adapters Guide"
|
||||
msgstr "LoRA 适配器指南"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/lora.md:3
|
||||
msgid "Overview"
|
||||
msgstr ""
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Like vLLM, vllm-kunlun supports LoRA "
|
||||
#~ "as well. The usage and more "
|
||||
#~ "details can be found in [vLLM "
|
||||
#~ "official "
|
||||
#~ "document](https://docs.vllm.ai/en/latest/features/lora.html)."
|
||||
#~ msgstr ""
|
||||
#~ "与 vLLM 类似，vllm-kunlun 也支持 "
|
||||
#~ "LoRA。用法及更多详情可参见 [vLLM "
|
||||
#~ "官方文档](https://docs.vllm.ai/en/latest/features/lora.html)。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "You can also refer to "
|
||||
#~ "[this](https://docs.vllm.ai/en/latest/models/supported_models.html"
|
||||
#~ "#list-of-text-only-language-models) "
|
||||
#~ "to find which models support LoRA "
|
||||
#~ "in vLLM."
|
||||
#~ msgstr ""
|
||||
#~ "你也可以参考[这个链接](https://docs.vllm.ai/en/latest/models/supported_models.html"
|
||||
#~ "#list-of-text-only-language-models)来查找哪些模型在"
|
||||
#~ " vLLM 中支持 LoRA。"
|
||||
|
||||
#~ msgid "Tips"
|
||||
#~ msgstr "提示"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "If you fail to run vllm-kunlun "
|
||||
#~ "with LoRA, you may follow [this "
|
||||
#~ "instruction](https://vllm-"
|
||||
#~ "kunlun.readthedocs.io/en/latest/user_guide/feature_guide/graph_mode.html"
|
||||
#~ "#fallback-to-eager-mode) to disable "
|
||||
#~ "graph mode and try again."
|
||||
#~ msgstr ""
|
||||
#~ "如果你在使用 LoRA 运行 vllm-kunlun "
|
||||
#~ "时失败，可以按照[此说明](https://vllm-"
|
||||
#~ "kunlun.readthedocs.io/en/latest/user_guide/feature_guide/graph_mode.html"
|
||||
#~ "#fallback-to-eager-mode)禁用图模式后再重试。"
|
||||
|
||||
@@ -0,0 +1,26 @@
|
||||
# SOME DESCRIPTIVE TITLE.
|
||||
# Copyright (C) 2025, vllm-kunlun team
|
||||
# This file is distributed under the same license as the vllm-kunlun
|
||||
# package.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: vllm-kunlun \n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2025-11-10 16:59+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language: zh_CN\n"
|
||||
"Language-Team: zh_CN <LL@li.org>\n"
|
||||
"Plural-Forms: nplurals=1; plural=0;\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/netloader.md:1
|
||||
msgid "Netloader Guide"
|
||||
msgstr ""
|
||||
|
||||
@@ -0,0 +1,198 @@
|
||||
# SOME DESCRIPTIVE TITLE.
|
||||
# Copyright (C) 2025, vllm-kunlun team
|
||||
# This file is distributed under the same license as the vllm-kunlun
|
||||
# package.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: vllm-kunlun\n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2025-11-10 16:59+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language: zh_CN\n"
|
||||
"Language-Team: zh_CN <LL@li.org>\n"
|
||||
"Plural-Forms: nplurals=1; plural=0;\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/quantization.md:1
|
||||
msgid "Quantization Guide"
|
||||
msgstr "量化指南"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Model quantization is a technique that"
|
||||
#~ " reduces the size and computational "
|
||||
#~ "requirements of a model by lowering "
|
||||
#~ "the data precision of the weights "
|
||||
#~ "and activation values in the model, "
|
||||
#~ "thereby saving the memory and improving"
|
||||
#~ " the inference speed."
|
||||
#~ msgstr "模型量化是一种通过降低模型中权重和激活值的数据精度，从而减少模型大小和计算需求的技术，这样可以节省内存并提高推理速度。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Since 0.9.0rc2 version, quantization feature"
|
||||
#~ " is experimentally supported in vLLM "
|
||||
#~ "Kunlun. Users can enable quantization "
|
||||
#~ "feature by specifying `--quantization kunlun`."
|
||||
#~ " Currently, only Qwen, DeepSeek series "
|
||||
#~ "models are well tested. We’ll support"
|
||||
#~ " more quantization algorithm and models "
|
||||
#~ "in the future."
|
||||
#~ msgstr ""
|
||||
#~ "自 0.9.0rc2 版本起，vLLM Kunlun 实验性地支持量化特性。用户可以通过指定"
|
||||
#~ " `--quantization kunlun` 启用量化功能。目前，只有 "
|
||||
#~ "Qwen、DeepSeek 系列模型经过了充分测试。未来我们将支持更多的量化算法和模型。"
|
||||
|
||||
#~ msgid "Install modelslim"
|
||||
#~ msgstr "安装 modelslim"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "To quantize a model, users should "
|
||||
#~ "install "
|
||||
#~ "[ModelSlim](https://gitcode.com/Kunlun/msit/blob/master/msmodelslim/README.md)"
|
||||
#~ " which is the Kunlun compression and"
|
||||
#~ " acceleration tool. It is an "
|
||||
#~ "affinity-based compression tool designed "
|
||||
#~ "for acceleration, using compression as "
|
||||
#~ "its core technology and built upon "
|
||||
#~ "the Kunlun platform."
|
||||
#~ msgstr "要对模型进行量化，用户应安装[ModelSlim](https://gitcode.com/Kunlun/msit/blob/master/msmodelslim/README.md)，这是昇腾的压缩与加速工具。它是一种基于亲和性的压缩工具，专为加速设计，以压缩为核心技术，并基于昇腾平台构建。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Currently, only the specific tag "
|
||||
#~ "[modelslim-"
|
||||
#~ "VLLM-8.1.RC1.b020_001](https://gitcode.com/Kunlun/msit/blob"
|
||||
#~ "/modelslim-VLLM-8.1.RC1.b020_001/msmodelslim/README.md) of"
|
||||
#~ " modelslim works with vLLM Kunlun. "
|
||||
#~ "Please do not install other version "
|
||||
#~ "until modelslim master version is "
|
||||
#~ "available for vLLM Kunlun in the "
|
||||
#~ "future."
|
||||
#~ msgstr ""
|
||||
#~ "目前，只有 modelslim 的特定标签 [modelslim-"
|
||||
#~ "VLLM-8.1.RC1.b020_001](https://gitcode.com/Kunlun/msit/blob"
|
||||
#~ "/modelslim-VLLM-8.1.RC1.b020_001/msmodelslim/README.md) 支持"
|
||||
#~ " vLLM Kunlun。在未来 modelslim 的主版本支持 vLLM "
|
||||
#~ "Kunlun 之前，请不要安装其他版本。"
|
||||
|
||||
#~ msgid "Install modelslim:"
|
||||
#~ msgstr "安装 modelslim："
|
||||
|
||||
#~ msgid "Quantize model"
|
||||
#~ msgstr "量化模型"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Take [DeepSeek-V2-Lite](https://modelscope.cn/models"
|
||||
#~ "/deepseek-ai/DeepSeek-V2-Lite) as an example, "
|
||||
#~ "you just need to download the "
|
||||
#~ "model, and then execute the convert "
|
||||
#~ "command. The command is shown below. "
|
||||
#~ "More info can be found in "
|
||||
#~ "modelslim doc [deepseek w8a8 dynamic "
|
||||
#~ "quantization docs](https://gitcode.com/Kunlun/msit/blob"
|
||||
#~ "/modelslim-"
|
||||
#~ "VLLM-8.1.RC1.b020_001/msmodelslim/example/DeepSeek/README.md#deepseek-v2-w8a8-dynamic%E9%87%8F%E5%8C%96)."
|
||||
#~ msgstr ""
|
||||
#~ "以 [DeepSeek-V2-Lite](https://modelscope.cn/models/deepseek-"
|
||||
#~ "ai/DeepSeek-V2-Lite) 为例，你只需要下载模型，然后执行转换命令。命令如下所示。更多信息可参考 "
|
||||
#~ "modelslim 文档 [deepseek w8a8 "
|
||||
#~ "动态量化文档](https://gitcode.com/Kunlun/msit/blob/modelslim-"
|
||||
#~ "VLLM-8.1.RC1.b020_001/msmodelslim/example/DeepSeek/README.md#deepseek-v2-w8a8-dynamic%E9%87%8F%E5%8C%96)。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "You can also download the quantized "
|
||||
#~ "model that we uploaded. Please note "
|
||||
#~ "that these weights should be used "
|
||||
#~ "for test only. For example, "
|
||||
#~ "https://www.modelscope.cn/models/vllm-kunlun/DeepSeek-V2"
|
||||
#~ "-Lite-W8A8"
|
||||
#~ msgstr ""
|
||||
#~ "你也可以下载我们上传的量化模型。请注意，这些权重仅应用于测试。例如：https://www.modelscope.cn/models"
|
||||
#~ "/vllm-kunlun/DeepSeek-V2-Lite-W8A8"
|
||||
|
||||
#~ msgid "Once convert action is done, there are two important files generated."
|
||||
#~ msgstr "转换操作完成后，会生成两个重要的文件。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "[config.json](https://www.modelscope.cn/models/vllm-"
|
||||
#~ "kunlun/DeepSeek-V2-Lite-"
|
||||
#~ "W8A8/file/view/master/config.json?status=1). Please make"
|
||||
#~ " sure that there is no "
|
||||
#~ "`quantization_config` field in it."
|
||||
#~ msgstr ""
|
||||
#~ "[config.json](https://www.modelscope.cn/models/vllm-"
|
||||
#~ "kunlun/DeepSeek-V2-Lite-"
|
||||
#~ "W8A8/file/view/master/config.json?status=1)。请确保其中没有 "
|
||||
#~ "`quantization_config` 字段。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "[quant_model_description.json](https://www.modelscope.cn/models"
|
||||
#~ "/vllm-kunlun/DeepSeek-V2-Lite-"
|
||||
#~ "W8A8/file/view/master/quant_model_description.json?status=1). "
|
||||
#~ "All the converted weights info are "
|
||||
#~ "recorded in this file."
|
||||
#~ msgstr ""
|
||||
#~ "[quant_model_description.json](https://www.modelscope.cn/models"
|
||||
#~ "/vllm-kunlun/DeepSeek-V2-Lite-"
|
||||
#~ "W8A8/file/view/master/quant_model_description.json?status=1)。所有被转换的权重信息都记录在该文件中。"
|
||||
|
||||
#~ msgid "Here is the full converted model files:"
|
||||
#~ msgstr "以下是完整转换后的模型文件："
|
||||
|
||||
#~ msgid "Run the model"
|
||||
#~ msgstr "运行模型"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Now, you can run the quantized "
|
||||
#~ "models with vLLM Kunlun. Here is "
|
||||
#~ "the example for online and offline "
|
||||
#~ "inference."
|
||||
#~ msgstr "现在，你可以使用 vLLM Kunlun 运行量化模型。下面是在线和离线推理的示例。"
|
||||
|
||||
#~ msgid "Offline inference"
|
||||
#~ msgstr "离线推理"
|
||||
|
||||
#~ msgid "Online inference"
|
||||
#~ msgstr "在线推理"
|
||||
|
||||
#~ msgid "FAQs"
|
||||
#~ msgstr "常见问题解答"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "1. How to solve the KeyError: "
|
||||
#~ "'xxx.layers.0.self_attn.q_proj.weight' problem?"
|
||||
#~ msgstr "1. 如何解决 KeyError: 'xxx.layers.0.self_attn.q_proj.weight' 问题？"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "First, make sure you specify `kunlun`"
|
||||
#~ " quantization method. Second, check if "
|
||||
#~ "your model is converted by this "
|
||||
#~ "`modelslim-VLLM-8.1.RC1.b020_001` modelslim version."
|
||||
#~ " Finally, if it still doesn't work,"
|
||||
#~ " please submit a issue, maybe some"
|
||||
#~ " new models need to be adapted."
|
||||
#~ msgstr ""
|
||||
#~ "首先，请确保你指定了 `kunlun` 量化方法。其次，检查你的模型是否由 `modelslim-"
|
||||
#~ "VLLM-8.1.RC1.b020_001` 这个 modelslim "
|
||||
#~ "版本转换。如果仍然无法使用，请提交一个 issue，可能有一些新模型需要适配。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "2. How to solve the error \"Could"
|
||||
#~ " not locate the configuration_deepseek.py\"?"
|
||||
#~ msgstr "2. 如何解决“无法找到 configuration_deepseek.py”错误？"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Please convert DeepSeek series models "
|
||||
#~ "using `modelslim-VLLM-8.1.RC1.b020_001` modelslim,"
|
||||
#~ " this version has fixed the missing"
|
||||
#~ " configuration_deepseek.py error."
|
||||
#~ msgstr ""
|
||||
#~ "请使用 `modelslim-VLLM-8.1.RC1.b020_001` 的 "
|
||||
#~ "modelslim 转换 DeepSeek 系列模型，该版本已修复缺少 "
|
||||
#~ "configuration_deepseek.py 的错误。"
|
||||
|
||||
@@ -0,0 +1,165 @@
|
||||
# SOME DESCRIPTIVE TITLE.
|
||||
# Copyright (C) 2025, vllm-kunlun team
|
||||
# This file is distributed under the same license as the vllm-kunlun
|
||||
# package.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: vllm-kunlun\n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2025-11-10 16:59+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language: zh_CN\n"
|
||||
"Language-Team: zh_CN <LL@li.org>\n"
|
||||
"Plural-Forms: nplurals=1; plural=0;\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/sleep_mode.md:1
|
||||
msgid "Sleep Mode Guide"
|
||||
msgstr "睡眠模式指南"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/sleep_mode.md:3
|
||||
msgid "Overview"
|
||||
msgstr "概述"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Sleep Mode is an API designed to"
|
||||
#~ " offload model weights and discard KV"
|
||||
#~ " cache from XPU memory. This "
|
||||
#~ "functionality is essential for reinforcement"
|
||||
#~ " learning (RL) post-training workloads, "
|
||||
#~ "particularly in online algorithms such "
|
||||
#~ "as PPO, GRPO, or DPO. During "
|
||||
#~ "training, the policy model typically "
|
||||
#~ "performs auto-regressive generation using "
|
||||
#~ "inference engines like vLLM, followed by"
|
||||
#~ " forward and backward passes for "
|
||||
#~ "optimization."
|
||||
#~ msgstr ""
|
||||
#~ "Sleep Mode 是一个用于卸载模型权重并清除 XPU 内存中 KV "
|
||||
#~ "缓存的 API。此功能对于强化学习（RL）后训练任务尤其重要，特别是在 PPO、GRPO 或 "
|
||||
#~ "DPO 等在线算法中。在训练过程中，策略模型通常会使用像 vLLM "
|
||||
#~ "这样的推理引擎进行自回归生成，然后进行前向和反向传播以进行优化。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Since the generation and training phases"
|
||||
#~ " may employ different model parallelism "
|
||||
#~ "strategies, it becomes crucial to free"
|
||||
#~ " KV cache and even offload model "
|
||||
#~ "parameters stored within vLLM during "
|
||||
#~ "training. This ensures efficient memory "
|
||||
#~ "utilization and avoids resource contention "
|
||||
#~ "on the XPU."
|
||||
#~ msgstr ""
|
||||
#~ "由于生成和训练阶段可能采用不同的模型并行策略，因此在训练过程中及时释放 KV 缓存，甚至卸载存储在 "
|
||||
#~ "vLLM 内的模型参数变得至关重要。这可以确保内存的高效利用，并避免 XPU 上的资源争用。"
|
||||
|
||||
#~ msgid "Getting started"
|
||||
#~ msgstr "快速上手"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "With `enable_sleep_mode=True`, the way we "
|
||||
#~ "manage memory(malloc, free) in vllm will"
|
||||
#~ " under a specific memory pool, during"
|
||||
#~ " loading model and initialize kv_caches,"
|
||||
#~ " we tag the memory as a map:"
|
||||
#~ " `{\"weight\": data, \"kv_cache\": data}`."
|
||||
#~ msgstr ""
|
||||
#~ "当 `enable_sleep_mode=True` 时，我们在 vllm "
|
||||
#~ "中管理内存（malloc, free）的方式会在一个特定的内存池下进行，在加载模型和初始化 kv_caches"
|
||||
#~ " 期间，我们会将内存打上标签，组织成一个映射：`{\"weight\": data, "
|
||||
#~ "\"kv_cache\": data}`。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "The engine(v0/v1) supports two sleep "
|
||||
#~ "levels to manage memory during idle "
|
||||
#~ "periods:"
|
||||
#~ msgstr "该引擎（v0/v1）支持两种睡眠等级，以在空闲期间管理内存："
|
||||
|
||||
#~ msgid "Level 1 Sleep"
|
||||
#~ msgstr "一级睡眠"
|
||||
|
||||
#~ msgid "Action: Offloads model weights and discards the KV cache."
|
||||
#~ msgstr "操作：卸载模型权重并清除KV缓存。"
|
||||
|
||||
#~ msgid "Memory: Model weights are moved to CPU memory; KV cache is forgotten."
|
||||
#~ msgstr "内存：模型权重被移动到CPU内存；KV缓存被清除。"
|
||||
|
||||
#~ msgid "Use Case: Suitable when reusing the same model later."
|
||||
#~ msgstr "用例：适用于之后需要重复使用同一个模型的情况。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Note: Ensure sufficient CPU memory is"
|
||||
#~ " available to hold the model weights."
|
||||
#~ msgstr "注意：请确保有足够的CPU内存来存储模型权重。"
|
||||
|
||||
#~ msgid "Level 2 Sleep"
|
||||
#~ msgstr "二级睡眠"
|
||||
|
||||
#~ msgid "Action: Discards both model weights and KV cache."
|
||||
#~ msgstr "操作：同时丢弃模型权重和KV缓存。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Memory: The content of both the "
|
||||
#~ "model weights and kv cache is "
|
||||
#~ "forgotten."
|
||||
#~ msgstr "内存：模型权重和kv缓存的内容都会被遗忘。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Use Case: Ideal when switching to "
|
||||
#~ "a different model or updating the "
|
||||
#~ "current one."
|
||||
#~ msgstr "用例：当切换到不同的模型或更新当前模型时非常理想。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Since this feature uses the low-"
|
||||
#~ "level API "
|
||||
#~ "[KunlunCL](https://www.hikunlun.com/document/detail/zh/CANNCommunityEdition/82RC1alpha002/API/appdevgapi/appdevgapi_07_0000.html),"
|
||||
#~ " in order to use sleep mode, "
|
||||
#~ "you should follow the [installation "
|
||||
#~ "guide](https://vllm-"
|
||||
#~ "kunlun.readthedocs.io/en/latest/installation.html) and "
|
||||
#~ "building from source, if you are "
|
||||
#~ "using v0.7.3, remember to set `export"
|
||||
#~ " COMPILE_CUSTOM_KERNELS=1`, for the latest "
|
||||
#~ "version(v0.9.x+), the environment variable "
|
||||
#~ "`COMPILE_CUSTOM_KERNELS` will be set 1 "
|
||||
#~ "by default while building from source."
|
||||
#~ msgstr ""
|
||||
#~ "由于此功能使用了底层 API "
|
||||
#~ "[KunlunCL](https://www.hikunlun.com/document/detail/zh/CANNCommunityEdition/82RC1alpha002/API/appdevgapi/appdevgapi_07_0000.html)，为了使用休眠模式，你应按照[安装指南](https"
|
||||
#~ "://vllm-"
|
||||
#~ "kunlun.readthedocs.io/en/latest/installation.html)进行操作，并从源码编译。如果你使用的是"
|
||||
#~ " v0.7.3，请记得设置 `export COMPILE_CUSTOM_KERNELS=1` "
|
||||
#~ "；对于最新版本（v0.9.x+），在从源码编译时环境变量 `COMPILE_CUSTOM_KERNELS` "
|
||||
#~ "默认会被设置为 1。"
|
||||
|
||||
#~ msgid "Usage"
|
||||
#~ msgstr "用法"
|
||||
|
||||
#~ msgid "The following is a simple example of how to use sleep mode."
|
||||
#~ msgstr "以下是如何使用睡眠模式的一个简单示例。"
|
||||
|
||||
#~ msgid "offline inference:"
|
||||
#~ msgstr "离线推理："
|
||||
|
||||
#~ msgid "online serving:"
|
||||
#~ msgstr "在线服务："
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Considering there may be a risk of"
|
||||
#~ " malicious access, please make sure "
|
||||
#~ "you are under a dev-mode, and "
|
||||
#~ "explicit specify the develop env: "
|
||||
#~ "`VLLM_SERVER_DEV_MODE` to expose these "
|
||||
#~ "endpoints(sleep/wake up)."
|
||||
#~ msgstr ""
|
||||
#~ "鉴于可能存在恶意访问的风险，请确保您处于开发模式，并明确指定开发环境：`VLLM_SERVER_DEV_MODE`，以便开放这些端点（sleep/wake"
|
||||
#~ " up）。"
|
||||
|
||||
@@ -0,0 +1,235 @@
|
||||
# SOME DESCRIPTIVE TITLE.
|
||||
# Copyright (C) 2025, vllm-kunlun team
|
||||
# This file is distributed under the same license as the vllm-kunlun
|
||||
# package.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: vllm-kunlun\n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2025-11-10 16:59+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language: zh_CN\n"
|
||||
"Language-Team: zh_CN <LL@li.org>\n"
|
||||
"Plural-Forms: nplurals=1; plural=0;\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/structured_output.md:1
|
||||
msgid "Structured Output Guide"
|
||||
msgstr "结构化输出指南"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/structured_output.md:3
|
||||
msgid "Overview"
|
||||
msgstr "概述"
|
||||
|
||||
#: ../../source/user_guide/feature_guide/structured_output.md:5
|
||||
#, fuzzy
|
||||
msgid "What is structured output?"
|
||||
msgstr "什么是结构化输出？"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "LLMs can be unpredictable when you "
|
||||
#~ "need output in specific formats. Think"
|
||||
#~ " of asking a model to generate "
|
||||
#~ "JSON - without guidance, it might "
|
||||
#~ "produce valid text that breaks JSON "
|
||||
#~ "specification. **Structured Output (also "
|
||||
#~ "called Guided Decoding)** enables LLMs "
|
||||
#~ "to generate outputs that follow a "
|
||||
#~ "desired structure while preserving the "
|
||||
#~ "non-deterministic nature of the system."
|
||||
#~ msgstr ""
|
||||
#~ "当你需要特定格式输出时，大型语言模型（LLMs）可能表现出不可预测性。比如让模型生成 "
|
||||
#~ "JSON，如果没有指导，模型可能会生成有效的文本，但这些文本却不符合 JSON "
|
||||
#~ "规范。**结构化输出（也称为引导解码）** 能让大型语言模型生成符合预期结构的输出，同时保留系统的非确定性特性。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "In simple terms, structured decoding "
|
||||
#~ "gives LLMs a “template” to follow. "
|
||||
#~ "Users provide a schema that “influences”"
|
||||
#~ " the model’s output, ensuring compliance"
|
||||
#~ " with the desired structure."
|
||||
#~ msgstr "简单来说，结构化解码为LLM提供了一个“模板”来遵循。用户提供一个模式来“影响”模型的输出，从而确保输出符合期望的结构。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ msgstr ""
|
||||
|
||||
#~ msgid "structured decoding"
|
||||
#~ msgstr "结构化解码"
|
||||
|
||||
#~ msgid "Structured Output in vllm-kunlun"
|
||||
#~ msgstr "vllm-kunlun 中的结构化输出"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Currently, vllm-kunlun supports **xgrammar**"
|
||||
#~ " and **guidance** backend for structured"
|
||||
#~ " output with vllm v1 engine."
|
||||
#~ msgstr "目前，vllm-kunlun 支持 vllm v1 引擎的结构化输出，后端包括 **xgrammar** 和 **guidance**。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "XGrammar introduces a new technique that"
|
||||
#~ " batch constrained decoding via pushdown"
|
||||
#~ " automaton (PDA). You can think of"
|
||||
#~ " a PDA as a “collection of "
|
||||
#~ "FSMs, and each FSM represents a "
|
||||
#~ "context-free grammar (CFG).” One "
|
||||
#~ "significant advantage of PDA is its "
|
||||
#~ "recursive nature, allowing us to execute"
|
||||
#~ " multiple state transitions. They also "
|
||||
#~ "include additional optimisation (for those "
|
||||
#~ "who are interested) to reduce grammar"
|
||||
#~ " compilation overhead. Besides, you can "
|
||||
#~ "also find more details about guidance"
|
||||
#~ " by yourself."
|
||||
#~ msgstr ""
|
||||
#~ "XGrammar 引入了一种通过下推自动机（PDA）进行批量约束解码的新技术。你可以把 PDA "
|
||||
#~ "理解为“有限状态机（FSM）的集合，每个 FSM 代表一个上下文无关文法（CFG）。” PDA "
|
||||
#~ "的一个重要优点是其递归特性，使我们能够执行多次状态转移。此外，PDA "
|
||||
#~ "还包含了额外的优化（供感兴趣的用户参考），以减少语法编译的开销。除此之外，你还可以自己找到更多关于指导的信息。"
|
||||
|
||||
#~ msgid "How to Use Structured Output?"
|
||||
#~ msgstr "如何使用结构化输出？"
|
||||
|
||||
#~ msgid "Online Inference"
|
||||
#~ msgstr "在线推理"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "You can also generate structured outputs"
|
||||
#~ " using the OpenAI's Completions and "
|
||||
#~ "Chat API. The following parameters are"
|
||||
#~ " supported, which must be added as"
|
||||
#~ " extra parameters:"
|
||||
#~ msgstr "你也可以使用 OpenAI 的 Completions 和 Chat API 生成结构化输出。支持以下参数，这些参数必须作为额外参数添加："
|
||||
|
||||
#~ msgid "`guided_choice`: the output will be exactly one of the choices."
|
||||
#~ msgstr "`guided_choice`：输出将会是其中一个选项。"
|
||||
|
||||
#~ msgid "`guided_regex`: the output will follow the regex pattern."
|
||||
#~ msgstr "`guided_regex`：输出将遵循正则表达式模式。"
|
||||
|
||||
#~ msgid "`guided_json`: the output will follow the JSON schema."
|
||||
#~ msgstr "`guided_json`：输出将遵循 JSON 架构。"
|
||||
|
||||
#~ msgid "`guided_grammar`: the output will follow the context free grammar."
|
||||
#~ msgstr "`guided_grammar`：输出将遵循上下文无关文法。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Structured outputs are supported by "
|
||||
#~ "default in the OpenAI-Compatible Server."
|
||||
#~ " You can choose to specify the "
|
||||
#~ "backend to use by setting the "
|
||||
#~ "`--guided-decoding-backend` flag to vllm"
|
||||
#~ " serve. The default backend is "
|
||||
#~ "`auto`, which will try to choose "
|
||||
#~ "an appropriate backend based on the "
|
||||
#~ "details of the request. You may "
|
||||
#~ "also choose a specific backend, along"
|
||||
#~ " with some options."
|
||||
#~ msgstr ""
|
||||
#~ "OpenAI 兼容服务器默认支持结构化输出。你可以通过设置 `--guided-decoding-"
|
||||
#~ "backend` 标志为 vllm serve 来指定要使用的后端。默认后端为 "
|
||||
#~ "`auto`，它会根据请求的详细信息尝试选择合适的后端。你也可以选择特定的后端，并设置一些选项。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Now let´s see an example for each"
|
||||
#~ " of the cases, starting with the "
|
||||
#~ "guided_choice, as it´s the easiest one:"
|
||||
#~ msgstr "现在让我们来看每种情况的示例，首先是 guided_choice，因为它是最简单的："
|
||||
|
||||
#~ msgid ""
|
||||
#~ "The next example shows how to use"
|
||||
#~ " the guided_regex. The idea is to "
|
||||
#~ "generate an email address, given a "
|
||||
#~ "simple regex template:"
|
||||
#~ msgstr "下一个例子展示了如何使用 guided_regex。其思路是基于一个简单的正则表达式模板生成一个电子邮件地址："
|
||||
|
||||
#~ msgid ""
|
||||
#~ "One of the most relevant features "
|
||||
#~ "in structured text generation is the "
|
||||
#~ "option to generate a valid JSON "
|
||||
#~ "with pre-defined fields and formats. "
|
||||
#~ "For this we can use the "
|
||||
#~ "guided_json parameter in two different "
|
||||
#~ "ways:"
|
||||
#~ msgstr ""
|
||||
#~ "在结构化文本生成中，最相关的特性之一是能够生成具有预定义字段和格式的有效 JSON。为此，我们可以通过两种不同的方式使用 "
|
||||
#~ "guided_json 参数："
|
||||
|
||||
#~ msgid "Using a JSON Schema."
|
||||
#~ msgstr "使用 JSON 架构。"
|
||||
|
||||
#~ msgid "Defining a Pydantic model and then extracting the JSON Schema from it."
|
||||
#~ msgstr "定义一个 Pydantic 模型，然后从中提取 JSON Schema。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "The next example shows how to use"
|
||||
#~ " the guided_json parameter with a "
|
||||
#~ "Pydantic model:"
|
||||
#~ msgstr "下一个示例展示了如何将 guided_json 参数与 Pydantic 模型一起使用："
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Finally we have the guided_grammar "
|
||||
#~ "option, which is probably the most "
|
||||
#~ "difficult to use, but it´s really "
|
||||
#~ "powerful. It allows us to define "
|
||||
#~ "complete languages like SQL queries. It"
|
||||
#~ " works by using a context free "
|
||||
#~ "EBNF grammar. As an example, we "
|
||||
#~ "can use to define a specific "
|
||||
#~ "format of simplified SQL queries:"
|
||||
#~ msgstr ""
|
||||
#~ "最后，我们有 guided_grammar 选项，这可能是最难使用的，但它非常强大。它允许我们定义完整的语言，比如"
|
||||
#~ " SQL 查询。它通过使用上下文无关的 EBNF 语法来实现。例如，我们可以用它来定义一种简化"
|
||||
#~ " SQL 查询的特定格式："
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Find more examples [here](https://github.com"
|
||||
#~ "/vllm-"
|
||||
#~ "project/vllm/blob/main/examples/offline_inference/structured_outputs.py)."
|
||||
#~ msgstr ""
|
||||
#~ "在[这里](https://github.com/vllm-"
|
||||
#~ "project/vllm/blob/main/examples/offline_inference/structured_outputs.py)可以找到更多示例。"
|
||||
|
||||
#~ msgid "Offline Inference"
|
||||
#~ msgstr "离线推理"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "To use Structured Output, we'll need "
|
||||
#~ "to configure the guided decoding using"
|
||||
#~ " the class `GuidedDecodingParams` inside "
|
||||
#~ "`SamplingParams`. The main available options"
|
||||
#~ " inside `GuidedDecodingParams` are:"
|
||||
#~ msgstr ""
|
||||
#~ "要使用结构化输出，我们需要在 `SamplingParams` 内通过 "
|
||||
#~ "`GuidedDecodingParams` 类配置引导解码。`GuidedDecodingParams` "
|
||||
#~ "中主要可用的选项有："
|
||||
|
||||
#~ msgid "json"
|
||||
#~ msgstr "json"
|
||||
|
||||
#~ msgid "regex"
|
||||
#~ msgstr "正则表达式"
|
||||
|
||||
#~ msgid "choice"
|
||||
#~ msgstr "选择"
|
||||
|
||||
#~ msgid "grammar"
|
||||
#~ msgstr "语法"
|
||||
|
||||
#~ msgid "One example for the usage of the choice parameter is shown below:"
|
||||
#~ msgstr "choice 参数用法的一个示例如下："
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Find more examples of other usages "
|
||||
#~ "[here](https://github.com/vllm-"
|
||||
#~ "project/vllm/blob/main/examples/offline_inference/structured_outputs.py)."
|
||||
#~ msgstr ""
|
||||
#~ "查看更多其他用法的示例 [在这里](https://github.com/vllm-"
|
||||
#~ "project/vllm/blob/main/examples/offline_inference/structured_outputs.py)。"
|
||||
|
||||
1880
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/release_notes.po
Normal file
1880
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/release_notes.po
Normal file
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,33 @@
|
||||
# Translations template for PROJECT.
|
||||
# Copyright (C) 2025 ORGANIZATION
|
||||
# This file is distributed under the same license as the PROJECT project.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: PROJECT VERSION\n"
|
||||
"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n"
|
||||
"POT-Creation-Date: 2025-11-10 16:59+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language-Team: LANGUAGE <LL@li.org>\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/support_matrix/index.md:5
|
||||
msgid "Support Matrix"
|
||||
msgstr "支持矩阵"
|
||||
|
||||
#: ../../source/user_guide/support_matrix/index.md:1
|
||||
#, fuzzy
|
||||
msgid "Features and Models"
|
||||
msgstr "特性与模型"
|
||||
|
||||
#: ../../source/user_guide/support_matrix/index.md:3
|
||||
#, fuzzy
|
||||
msgid "This section provides a detailed matrix supported by vLLM Kunlun."
|
||||
msgstr "本节提供了 vLLM Kunlun 的详细支持矩阵。"
|
||||
|
||||
@@ -0,0 +1,221 @@
|
||||
# SOME DESCRIPTIVE TITLE.
|
||||
# Copyright (C) 2025, vllm-kunlun team
|
||||
# This file is distributed under the same license as the vllm-kunlun
|
||||
# package.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: vllm-kunlun\n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2025-11-10 16:59+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language: zh_CN\n"
|
||||
"Language-Team: zh_CN <LL@li.org>\n"
|
||||
"Plural-Forms: nplurals=1; plural=0;\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/support_matrix/supported_features.md:1
|
||||
msgid "Supported Features"
|
||||
msgstr ""
|
||||
|
||||
#: ../../source/user_guide/support_matrix/supported_features.md:3
|
||||
msgid "The feature support principle of vLLM"
|
||||
msgstr ""
|
||||
|
||||
#~ msgid "Feature Support"
|
||||
#~ msgstr "功能支持"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "The feature support principle of vLLM"
|
||||
#~ " Kunlun is: **aligned with the "
|
||||
#~ "vLLM**. We are also actively "
|
||||
#~ "collaborating with the community to "
|
||||
#~ "accelerate support."
|
||||
#~ msgstr "vLLM Kunlun 的特性支持原则是：**与 vLLM 保持一致**。我们也在积极与社区合作，加快支持进度。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "You can check the [support status "
|
||||
#~ "of vLLM V1 Engine][v1_user_guide]. Below "
|
||||
#~ "is the feature support status of "
|
||||
#~ "vLLM Kunlun:"
|
||||
#~ msgstr "你可以查看 [vLLM V1 引擎的支持状态][v1_user_guide]。下面是 vLLM Kunlun 的功能支持情况："
|
||||
|
||||
#~ msgid "Feature"
|
||||
#~ msgstr "特性"
|
||||
|
||||
#~ msgid "vLLM V0 Engine"
|
||||
#~ msgstr "vLLM V0 引擎"
|
||||
|
||||
#~ msgid "vLLM V1 Engine"
|
||||
#~ msgstr "vLLM V1 引擎"
|
||||
|
||||
#~ msgid "Next Step"
|
||||
#~ msgstr "下一步"
|
||||
|
||||
#~ msgid "Chunked Prefill"
|
||||
#~ msgstr "分块预填充"
|
||||
|
||||
#~ msgid "🟢 Functional"
|
||||
#~ msgstr "🟢 功能性"
|
||||
|
||||
#~ msgid "Functional, see detail note: [Chunked Prefill][cp]"
|
||||
#~ msgstr "功能性，详见说明：[分块预填充][cp]"
|
||||
|
||||
#~ msgid "Automatic Prefix Caching"
|
||||
#~ msgstr "自动前缀缓存"
|
||||
|
||||
#~ msgid "Functional, see detail note: [vllm-kunlun#732][apc]"
|
||||
#~ msgstr "可用，请参见详细说明：[vllm-kunlun#732][apc]"
|
||||
|
||||
#~ msgid "LoRA"
|
||||
#~ msgstr "LoRA"
|
||||
|
||||
#~ msgid "[vllm-kunlun#396][multilora], [vllm-kunlun#893][v1 multilora]"
|
||||
#~ msgstr "[vllm-kunlun#396][multilora]，[vllm-kunlun#893][v1 multilora]"
|
||||
|
||||
#~ msgid "Prompt adapter"
|
||||
#~ msgstr "提示适配器"
|
||||
|
||||
#~ msgid "🔴 No plan"
|
||||
#~ msgstr "🔴 无计划"
|
||||
|
||||
#~ msgid "This feature has been deprecated by vllm."
|
||||
#~ msgstr "此功能已被 vllm 弃用。"
|
||||
|
||||
#~ msgid "Speculative decoding"
|
||||
#~ msgstr "猜测式解码"
|
||||
|
||||
#~ msgid "Basic support"
|
||||
#~ msgstr "基础支持"
|
||||
|
||||
#~ msgid "Pooling"
|
||||
#~ msgstr "池化"
|
||||
|
||||
#~ msgid "🟡 Planned"
|
||||
#~ msgstr "🟡 计划中"
|
||||
|
||||
#~ msgid "CI needed and adapting more models; V1 support rely on vLLM support."
|
||||
#~ msgstr "需要持续集成（CI）并适配更多模型；V1 的支持依赖于 vLLM 的支持。"
|
||||
|
||||
#~ msgid "Enc-dec"
|
||||
#~ msgstr "Enc-dec（编码-解码）"
|
||||
|
||||
#~ msgid "🔴 NO plan"
|
||||
#~ msgstr "🔴 没有计划"
|
||||
|
||||
#~ msgid "Plan in 2025.06.30"
|
||||
#~ msgstr "2025.06.30 的计划"
|
||||
|
||||
#~ msgid "Multi Modality"
|
||||
#~ msgstr "多模态"
|
||||
|
||||
#~ msgid "[Tutorial][multimodal], optimizing and adapting more models"
|
||||
#~ msgstr "[教程][multimodal]，优化和适配更多模型"
|
||||
|
||||
#~ msgid "LogProbs"
|
||||
#~ msgstr "LogProbs"
|
||||
|
||||
#~ msgid "CI needed"
|
||||
#~ msgstr "需要持续集成（CI）"
|
||||
|
||||
#~ msgid "Prompt logProbs"
|
||||
#~ msgstr "提示 logProbs"
|
||||
|
||||
#~ msgid "Async output"
|
||||
#~ msgstr "异步输出"
|
||||
|
||||
#~ msgid "Multi step scheduler"
|
||||
#~ msgstr "多步调度器"
|
||||
|
||||
#~ msgid "🔴 Deprecated"
|
||||
#~ msgstr "🔴 已弃用"
|
||||
|
||||
#~ msgid "[vllm#8779][v1_rfc], replaced by [vLLM V1 Scheduler][v1_scheduler]"
|
||||
#~ msgstr "[vllm#8779][v1_rfc]，已被 [vLLM V1 调度器][v1_scheduler] 替代"
|
||||
|
||||
#~ msgid "Best of"
|
||||
#~ msgstr "精选"
|
||||
|
||||
#~ msgid "[vllm#13361][best_of], CI needed"
|
||||
#~ msgstr "[vllm#13361][best_of]，需要持续集成（CI）"
|
||||
|
||||
#~ msgid "Beam search"
|
||||
#~ msgstr "束搜索"
|
||||
|
||||
#~ msgid "Guided Decoding"
|
||||
#~ msgstr "引导解码"
|
||||
|
||||
#~ msgid "[vllm-kunlun#177][guided_decoding]"
|
||||
#~ msgstr "[vllm-kunlun#177][guided_decoding]"
|
||||
|
||||
#~ msgid "Tensor Parallel"
|
||||
#~ msgstr "张量并行"
|
||||
|
||||
#~ msgid "Pipeline Parallel"
|
||||
#~ msgstr "流水线并行"
|
||||
|
||||
#~ msgid "Expert Parallel"
|
||||
#~ msgstr "专家并行"
|
||||
|
||||
#~ msgid "CI needed; No plan on V0 support"
|
||||
#~ msgstr "需要持续集成；没有支持V0的计划"
|
||||
|
||||
#~ msgid "Data Parallel"
|
||||
#~ msgstr "数据并行"
|
||||
|
||||
#~ msgid "CI needed; No plan on V0 support"
|
||||
#~ msgstr "需要 CI；暂无 V0 支持计划"
|
||||
|
||||
#~ msgid "Prefill Decode Disaggregation"
|
||||
#~ msgstr "预填充 解码 拆分"
|
||||
|
||||
#~ msgid "1P1D available, working on xPyD and V1 support."
|
||||
#~ msgstr "1P1D 已可用，正在开发 xPyD 和 V1 支持。"
|
||||
|
||||
#~ msgid "Quantization"
|
||||
#~ msgstr "量化"
|
||||
|
||||
#~ msgid "W8A8 available, CI needed; working on more quantization method support"
|
||||
#~ msgstr "W8A8 已可用，需要持续集成（CI）；正在开发对更多量化方法的支持。"
|
||||
|
||||
#~ msgid "Graph Mode"
|
||||
#~ msgstr "图模式"
|
||||
|
||||
#~ msgid "🔵 Experimental"
|
||||
#~ msgstr "🔵 实验性"
|
||||
|
||||
#~ msgid "Experimental, see detail note: [vllm-kunlun#767][graph_mode]"
|
||||
#~ msgstr "实验性功能，详见说明：[vllm-kunlun#767][graph_mode]"
|
||||
|
||||
#~ msgid "Sleep Mode"
|
||||
#~ msgstr "睡眠模式"
|
||||
|
||||
#~ msgid "level=1 available, CI needed, working on V1 support"
|
||||
#~ msgstr "level=1 可用，需要CI，正在开发 V1 支持"
|
||||
|
||||
#~ msgid "🟢 Functional: Fully operational, with ongoing optimizations."
|
||||
#~ msgstr "🟢 功能性：完全可用，正在持续优化中。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "🔵 Experimental: Experimental support, "
|
||||
#~ "interfaces and functions may change."
|
||||
#~ msgstr "🔵 实验性：实验性支持，接口和功能可能会发生变化。"
|
||||
|
||||
#~ msgid "🚧 WIP: Under active development, will be supported soon."
|
||||
#~ msgstr "🚧 WIP：正在积极开发中，很快将会支持。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "🟡 Planned: Scheduled for future "
|
||||
#~ "implementation (some may have open "
|
||||
#~ "PRs/RFCs)."
|
||||
#~ msgstr "🟡 计划中：已安排将来实现（其中一些可能已有开放的PR/RFC）。"
|
||||
|
||||
#~ msgid "🔴 NO plan / Deprecated: No plan for V0 or deprecated by vLLM v1."
|
||||
#~ msgstr "🔴 没有计划 / 已弃用：V0 没有计划或已被 vLLM v1 弃用。"
|
||||
|
||||
@@ -0,0 +1,168 @@
|
||||
# SOME DESCRIPTIVE TITLE.
|
||||
# Copyright (C) 2025, vllm-kunlun team
|
||||
# This file is distributed under the same license as the vllm-kunlun
|
||||
# package.
|
||||
# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
|
||||
#
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: vllm-kunlun\n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2025-11-10 16:59+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language: zh_CN\n"
|
||||
"Language-Team: zh_CN <LL@li.org>\n"
|
||||
"Plural-Forms: nplurals=1; plural=0;\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
"Content-Type: text/plain; charset=utf-8\n"
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.17.0\n"
|
||||
|
||||
#: ../../source/user_guide/support_matrix/supported_models.md:1
|
||||
#, fuzzy
|
||||
msgid "Supported Models"
|
||||
msgstr "支持"
|
||||
|
||||
#~ msgid "Model Support"
|
||||
#~ msgstr "模型支持"
|
||||
|
||||
#~ msgid "Text-only Language Models"
|
||||
#~ msgstr "纯文本语言模型"
|
||||
|
||||
#~ msgid "Generative Models"
|
||||
#~ msgstr "生成模型"
|
||||
|
||||
#~ msgid "Model"
|
||||
#~ msgstr "模型"
|
||||
|
||||
#~ msgid "Note"
|
||||
#~ msgstr "注释"
|
||||
|
||||
#~ msgid "DeepSeek v3"
|
||||
#~ msgstr "DeepSeek v3"
|
||||
|
||||
#~ msgid "✅"
|
||||
#~ msgstr "✅"
|
||||
|
||||
#~ msgid "DeepSeek R1"
|
||||
#~ msgstr "DeepSeek R1"
|
||||
|
||||
#~ msgid "DeepSeek Distill (Qwen/LLama)"
|
||||
#~ msgstr "DeepSeek 精炼（Qwen/LLama）"
|
||||
|
||||
#~ msgid "Qwen3"
|
||||
#~ msgstr "Qwen3"
|
||||
|
||||
#~ msgid "Qwen3-Moe"
|
||||
#~ msgstr "Qwen3-Moe"
|
||||
|
||||
#~ msgid "Qwen2.5"
|
||||
#~ msgstr "Qwen2.5"
|
||||
|
||||
#~ msgid "QwQ-32B"
|
||||
#~ msgstr "QwQ-32B"
|
||||
|
||||
#~ msgid "LLama3.1/3.2"
|
||||
#~ msgstr "LLama3.1/3.2"
|
||||
|
||||
#~ msgid "Internlm"
|
||||
#~ msgstr "Internlm"
|
||||
|
||||
#~ msgid "Baichuan"
|
||||
#~ msgstr "百川"
|
||||
|
||||
#~ msgid "Phi-4-mini"
|
||||
#~ msgstr "Phi-4-mini"
|
||||
|
||||
#~ msgid "MiniCPM"
|
||||
#~ msgstr "MiniCPM"
|
||||
|
||||
#~ msgid "MiniCPM3"
|
||||
#~ msgstr "MiniCPM3"
|
||||
|
||||
#~ msgid "LLama4"
|
||||
#~ msgstr "LLama4"
|
||||
|
||||
#~ msgid "Mistral"
|
||||
#~ msgstr "Mistral"
|
||||
|
||||
#~ msgid "Need test"
|
||||
#~ msgstr "需要测试"
|
||||
|
||||
#~ msgid "DeepSeek v2.5"
|
||||
#~ msgstr "DeepSeek v2.5"
|
||||
|
||||
#~ msgid "Gemma-2"
|
||||
#~ msgstr "Gemma-2"
|
||||
|
||||
#~ msgid "Mllama"
|
||||
#~ msgstr "Mllama"
|
||||
|
||||
#~ msgid "Gemma-3"
|
||||
#~ msgstr "Gemma-3"
|
||||
|
||||
#~ msgid "❌"
|
||||
#~ msgstr "❌"
|
||||
|
||||
#~ msgid "[#496](https://github.com/vllm-project/vllm-kunlun/issues/496)"
|
||||
#~ msgstr "[#496](https://github.com/vllm-project/vllm-kunlun/issues/496)"
|
||||
|
||||
#~ msgid "ChatGLM"
|
||||
#~ msgstr "ChatGLM"
|
||||
|
||||
#~ msgid "[#554](https://github.com/vllm-project/vllm-kunlun/issues/554)"
|
||||
#~ msgstr "[#554](https://github.com/vllm-project/vllm-kunlun/issues/554)"
|
||||
|
||||
#~ msgid "Pooling Models"
|
||||
#~ msgstr "池化模型"
|
||||
|
||||
#~ msgid "XLM-RoBERTa-based"
|
||||
#~ msgstr "基于XLM-RoBERTa"
|
||||
|
||||
#~ msgid "Molmo"
|
||||
#~ msgstr "Molmo"
|
||||
|
||||
#~ msgid "Multimodal Language Models"
|
||||
#~ msgstr "多模态语言模型"
|
||||
|
||||
#~ msgid "Qwen2-VL"
|
||||
#~ msgstr "Qwen2-VL"
|
||||
|
||||
#~ msgid "Qwen2.5-VL"
|
||||
#~ msgstr "Qwen2.5-VL"
|
||||
|
||||
#~ msgid "LLaVA 1.5"
|
||||
#~ msgstr "LLaVA 1.5"
|
||||
|
||||
#~ msgid "LLaVA 1.6"
|
||||
#~ msgstr "LLaVA 1.6"
|
||||
|
||||
#~ msgid "[#553](https://github.com/vllm-project/vllm-kunlun/issues/553)"
|
||||
#~ msgstr "[#553](https://github.com/vllm-project/vllm-kunlun/issues/553)"
|
||||
|
||||
#~ msgid "InternVL2"
|
||||
#~ msgstr "InternVL2"
|
||||
|
||||
#~ msgid "InternVL2.5"
|
||||
#~ msgstr "InternVL2.5"
|
||||
|
||||
#~ msgid "Qwen2-Audio"
|
||||
#~ msgstr "Qwen2-Audio"
|
||||
|
||||
#~ msgid "LLaVA-Next"
|
||||
#~ msgstr "LLaVA-Next"
|
||||
|
||||
#~ msgid "LLaVA-Next-Video"
|
||||
#~ msgstr "LLaVA-Next-Video"
|
||||
|
||||
#~ msgid "Phi-3-Vison/Phi-3.5-Vison"
|
||||
#~ msgstr "Phi-3-Vison/Phi-3.5-Vison"
|
||||
|
||||
#~ msgid "GLM-4v"
|
||||
#~ msgstr "GLM-4v"
|
||||
|
||||
#~ msgid "Ultravox"
|
||||
#~ msgstr "Ultravox"
|
||||
|
||||
Reference in New Issue
Block a user