Skip to content

Commit 9e0c6ba

Browse files
vllm-ascend-ciwangxiyuan
vllm-ascend-ci
and
wangxiyuan
authored
[Doc] Translated Doc files 2026-07-08 (vllm-project#11655)
## Auto-Translation Summary Translated **52** file(s): - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/community/slash-commands.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/ModelRunner_prepare_inputs.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/cpu_binding.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/quantization.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/doc_writing.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/testing.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_lm_eval.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance_and_debug/optimization_and_tuning.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/faqs.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/installation.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/dynamic_chunked_pipeline_parallel.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/long_sequence_context_parallel_multi_node.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/long_sequence_context_parallel_single_node.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/pd_disaggregation_mooncake_multi_node.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/hardwares/310p.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/DeepSeek-R1.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/DeepSeek-V3.1.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/DeepSeek-V3.2.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/DeepSeek-V4-Flash.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/DeepSeek-V4-Pro.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/DeepSeekOCR2.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/GLM4.x.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/GLM5.2.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/GLM5.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Hunyuan-A13B-Instruct.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Hy3-preview.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/InternVL3.5.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Kimi-K2-Thinking.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Kimi-K2.5.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Kimi-K2.6.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/LLaVA-OneVision-Qwen2-0.5B-OV.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Mixtral-8x7B-Instruct-v0.1.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/PaddleOCR-VL.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-235B-A22B.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-30B-A3B.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-Coder-30B-A3B.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-Dense.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-Next.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-Omni-30B-A3B-Thinking.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-VL-235B-A22B-Instruct.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-VL-Reranker.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3.5-27B-Qwen3.6-27B.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3_reranker.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/deployment_guide/using_volcano_kthena.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/cpu_binding.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/dynamic_chunk_pipeline_parallel.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/flash_attention.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/graph_mode.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/kv_pool.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/quantization.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/ucm_deployment.po</code> - <code>/home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/support_matrix/supported_models.po</code> --- [Workflow run](https://github.com/vllm-project/vllm-ascend/actions/runs/28957659620) - vLLM version: v0.23.0 - vLLM main: vllm-project/vllm@1f486d9 Signed-off-by: wangxiyuan <wangxiyuan@users.noreply.github.com> Co-authored-by: wangxiyuan <wangxiyuan@users.noreply.github.com>
1 parent 59e6f47 commit 9e0c6ba

52 files changed

Lines changed: 792 additions & 381 deletions

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎docs/source/locale/zh_CN/LC_MESSAGES/community/slash-commands.po‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -291,16 +291,16 @@ msgstr ""
291291
"进行验证。"
292292

293293
msgid "**Examples:**"
294-
msgstr ""
294+
msgstr "**示例：**"
295295

296296
msgid "**Usage:**"
297-
msgstr ""
297+
msgstr "**用法：**"
298298

299299
msgid "**Examples:**"
300-
msgstr ""
300+
msgstr "**示例：**"
301301

302302
msgid "**Usage:**"
303-
msgstr ""
303+
msgstr "**用法：**"
304304

305305
msgid "**Examples:**"
306-
msgstr ""
306+
msgstr "**示例：**"

‎docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/ModelRunner_prepare_inputs.po‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -467,7 +467,7 @@ msgid ""
467467
msgstr "希望本文档能帮助你更好地理解 vLLM 如何为模型前向传播准备输入。如果你有任何好的想法，欢迎向我们贡献。"
468468

469469
msgid "#### Obtain inputs"
470-
msgstr ""
470+
msgstr "#### 获取输入"
471471

472472
msgid "#### Build inputs attention metadata"
473-
msgstr ""
473+
msgstr "#### 构建输入注意力元数据"

‎docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/cpu_binding.po‎

Lines changed: 121 additions & 20 deletions
Large diffs are not rendered by default.

‎docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/quantization.po‎

Lines changed: 22 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -130,42 +130,48 @@ msgid ""
130130
msgstr "**粒度：** 指缩放因子计算的范围（例如 per-tensor、per-channel、per-group）。"
131131

132132
msgid "# Quantization Adaptation Guide"
133-
msgstr ""
133+
msgstr "# 量化适配指南"
134134

135135
msgid "## Quantization Feature Introduction"
136-
msgstr ""
136+
msgstr "## 量化特性介绍"
137137

138138
msgid "### Quantization Inference Process"
139-
msgstr ""
139+
msgstr "### 量化推理流程"
140140

141141
msgid "### Quantization Algorithm Adaptation"
142-
msgstr ""
142+
msgstr "### 量化算法适配"
143143

144144
msgid ""
145145
"- **Step 1: Algorithm Design**. Define the algorithm ID (e.g., `W4A8_DYNAMIC`), determine supported layers (linear, moe, attention), and design the quantization scheme (static/dynamic, pertensor/perchannel/pergroup).\n"
146146
"- **Step 2: Registration**. Use the `@register_scheme` decorator in `vllm_ascend/quantization/methods/registry.py` to register your quantization scheme class."
147147
msgstr ""
148+
"- **第一步：算法设计**。定义算法ID（例如 `W4A8_DYNAMIC`），确定支持的层（线性层、MoE层、注意力层），并设计量化方案（静态/动态、逐张量/逐通道/逐分组）。\n"
149+
"- **第二步：注册**。在 `vllm_ascend/quantization/methods/registry.py` 中使用 `@register_scheme` 装饰器注册您的量化方案类。"
148150

149151
msgid ""
150152
"- **Step 3: Implementation**. Create an algorithm implementation file, such as `vllm_ascend/quantization/methods/w4a8.py`, and implement the method class and logic.\n"
151153
"- **Step 4: Testing**. Use your algorithm to generate quantization configurations and verify correctness and performance on target models and hardware."
152154
msgstr ""
155+
"- **第三步：实现**。创建算法实现文件，例如 `vllm_ascend/quantization/methods/w4a8.py`，并实现方法类和逻辑。\n"
156+
"- **第四步：测试**。使用您的算法生成量化配置，并在目标模型和硬件上验证正确性和性能。"
153157

154158
msgid "### Quantized Model Adaptation"
155-
msgstr ""
159+
msgstr "### 量化模型适配"
156160

157161
msgid ""
158162
"- The original model has been successfully adapted in `vLLM Ascend`.\n"
159163
"- **Fused Module Mapping**: Add the model's `model_type` to `packed_modules_model_mapping` in `vllm_ascend/quantization/modelslim_config.py` (e.g., `qkv_proj`, `gate_up_proj`, `experts`) to ensure sharding consistency and correct loading."
160164
msgstr ""
165+
"- 原始模型已在 `vLLM Ascend` 中成功适配。\n"
166+
"- **融合模块映射**：将模型的 `model_type` 添加到 `vllm_ascend/quantization/modelslim_config.py` 中的 `packed_modules_model_mapping`（例如 `qkv_proj`、`gate_up_proj`、`experts`），以确保分片一致性和正确加载。"
161167

162168
msgid ""
163169
"- All quantization algorithms used by the quantized model have been "
164170
"integrated into the `quantization` module."
165-
msgstr ""
171+
msgstr "- 量化模型使用的所有量化算法均已集成到 `quantization` 模块中。"
166172

167173
msgid "## Currently Supported Quantization Algorithms"
168-
msgstr ""
174+
msgstr "## 当前支持的量化算法"
169175

170176
msgid ""
171177
"| Algorithm | Weight | Activation | Weight Granularity | Activation Granularity | Type | Description |\n"
@@ -178,6 +184,15 @@ msgid ""
178184
"| `W4A4_FLATQUANT_DYNAMIC` | INT4 | INT4 | Per-Channel | Per-Token | Dynamic | Uses FlatQuant for activation distribution smoothing before 4-bit dynamic quantization, with additional matrix multiplications for precision preservation |\n"
179185
"| `W8A8_MIX` | INT8 | INT8 | Per-Channel | Per-Tensor/Token | Mixed | We support two deployment modes: PD Colocation (dynamic quantization for both P and D) and PD Disaggregation (dynamic-quant P and static-quant D) |"
180186
msgstr ""
187+
"| 算法 | 权重 | 激活值 | 权重粒度 | 激活值粒度 | 类型 | 描述 |\n"
188+
"| ------------------------ | ------ | --------- | ------------------ | ---------------------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n"
189+
"| `W4A16` | INT4 | FP16/BF16 | 逐分组 | 逐张量 | 静态 | 4位权重量化与16位激活精度，专为MoE模型专家层设计，支持int32格式权重打包 |\n"
190+
"| `W8A16` | INT8 | FP16/BF16 | 逐通道 | 逐张量 | 静态 | 8位权重量化与16位激活精度，平衡精度与性能，适用于线性层 |\n"
191+
"| `W8A8` | INT8 | INT8 | 逐通道 | 逐张量 | 静态 | 静态激活量化，适用于需要高精度的场景 |\n"
192+
"| `W8A8_DYNAMIC` | INT8 | INT8 | 逐通道 | 逐Token | 动态 | 动态激活量化，逐Token计算缩放因子 |\n"
193+
"| `W4A8_DYNAMIC` | INT4 | INT8 | 逐分组 | 逐Token | 动态 | 支持直接逐通道量化为4位和两步量化（先逐通道量化为8位，再逐分组量化为4位） |\n"
194+
"| `W4A4_FLATQUANT_DYNAMIC` | INT4 | INT4 | 逐通道 | 逐Token | 动态 | 使用FlatQuant在4位动态量化前平滑激活值分布，通过额外矩阵乘法保持精度 |\n"
195+
"| `W8A8_MIX` | INT8 | INT8 | 逐通道 | 逐张量/Token | 混合 | 支持两种部署模式：PD共部署（P和D均使用动态量化）和PD分离部署（P使用动态量化，D使用静态量化） |"
181196

182197
#~ msgid "Quantization Adaptation Guide"
183198
#~ msgstr "量化适配指南"

‎docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/doc_writing.po‎

Lines changed: 12 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -387,34 +387,40 @@ msgstr ""
387387
"`GeneratedScript.language`，以便 Sphinx 能够正确高亮生成的文字块。"
388388

389389
msgid "Write the doc block like this:"
390-
msgstr ""
390+
msgstr "请按如下方式编写文档块："
391391

392392
msgid ""
393393
"set -eux\n"
394394
"{{ generated }}"
395395
msgstr ""
396+
"set -eux\n"
397+
"{{ generated }}"
396398

397399
msgid "Write the doc block like this:"
398-
msgstr ""
400+
msgstr "请按如下方式编写文档块："
399401

400402
msgid "Write the doc block like this:"
401-
msgstr ""
403+
msgstr "请按如下方式编写文档块："
402404

403405
msgid ""
404406
"set -eux\n"
405407
"{{ generated }}"
406408
msgstr ""
409+
"set -eux\n"
410+
"{{ generated }}"
407411

408412
msgid "Generated shell script:"
409-
msgstr ""
413+
msgstr "生成的Shell脚本："
410414

411415
msgid "Write the doc block like this:"
412-
msgstr ""
416+
msgstr "请按如下方式编写文档块："
413417

414418
msgid ""
415419
"set -eux\n"
416420
"{{ generated }}"
417421
msgstr ""
422+
"set -eux\n"
423+
"{{ generated }}"
418424

419425
msgid "Generated shell script:"
420-
msgstr ""
426+
msgstr "生成的Shell脚本："

‎docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/testing.po‎

Lines changed: 10 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -188,31 +188,31 @@ msgstr ""
188188

189189
msgid ""
190190
"After starting the container, you should install the required packages:"
191-
msgstr ""
191+
msgstr "启动容器后，您需要安装所需的软件包："
192192

193193
msgid "=== \"Local (CPU)\""
194-
msgstr ""
194+
msgstr "=== \"本地（CPU）\""
195195

196196
msgid "=== \"Local (CPU)\""
197-
msgstr ""
197+
msgstr "=== \"本地（CPU）\""
198198

199199
msgid "=== \"Single-card\""
200-
msgstr ""
200+
msgstr "=== \"单卡\""
201201

202202
msgid "=== \"Multi-card\""
203-
msgstr ""
203+
msgstr "=== \"多卡\""
204204

205205
msgid "You can run tests with `pytest` as well. Typical examples:"
206-
msgstr ""
206+
msgstr "您也可以使用 `pytest` 运行测试。典型示例如下："
207207

208208
msgid "=== \"Local (CPU)\""
209-
msgstr ""
209+
msgstr "=== \"本地（CPU）\""
210210

211211
msgid "You can't run the E2E test on CPUs."
212-
msgstr ""
212+
msgstr "无法在CPU上运行端到端测试。"
213213

214214
msgid "=== \"Single-card\""
215-
msgstr ""
215+
msgstr "=== \"单卡\""
216216

217217
msgid "=== \"Multi-card\""
218-
msgstr ""
218+
msgstr "=== \"多卡\""

‎docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_lm_eval.po‎

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -112,14 +112,16 @@ msgstr ""
112112
"[5]: https://github.com/EleutherAI/lm-evaluation-harness/blob/main/docs/README.md"
113113

114114
msgid "Install lm-eval in the container:"
115-
msgstr ""
115+
msgstr "在容器中安装 lm-eval："
116116

117117
msgid ""
118118
"The Docker container is launched with `VLLM_USE_MODELSCOPE=True`, which may\n"
119119
" cause lm-eval to download datasets from ModelScope instead of HuggingFace.\n"
120120
" Setting `USE_MODELSCOPE_HUB=0` disables this behavior so that lm-eval can\n"
121121
" fetch datasets from HuggingFace correctly."
122122
msgstr ""
123+
"Docker 容器启动时设置了 `VLLM_USE_MODELSCOPE=True`，这可能导致 lm-eval 从 ModelScope 而非 HuggingFace 下载数据集。\n"
124+
" 设置 `USE_MODELSCOPE_HUB=0` 可禁用此行为，使 lm-eval 能够正确地从 HuggingFace 获取数据集。"
123125

124126
msgid "Run the following command:"
125-
msgstr ""
127+
msgstr "运行以下命令："

‎docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance_and_debug/optimization_and_tuning.po‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -260,19 +260,19 @@ msgstr ""
260260
"- 值越高，线程越倾向于停留在同一 CPU 核心上"
261261

262262
msgid "Purpose"
263-
msgstr ""
263+
msgstr "目的"
264264

265265
msgid "Benefits"
266-
msgstr ""
266+
msgstr "优势"
267267

268268
msgid "Purpose"
269-
msgstr ""
269+
msgstr "目的"
270270

271271
msgid "Benefits"
272-
msgstr ""
272+
msgstr "优势"
273273

274274
msgid "Purpose"
275-
msgstr ""
275+
msgstr "目的"
276276

277277
msgid "Benefits"
278-
msgstr ""
278+
msgstr "优势"

0 commit comments

Comments
 (0)