[Doc] AIDD Phase II Revision (vllm-project#13162)

### What this PR does / why we need it?
This PR performs various documentation revisions and cleanups across
multiple model tutorial and guide files, including:
- Correcting typos and improving grammar/clarity (e.g., changing "Single
card" to "Single-card" and "Multi cards" to "Multi-cards" in
`testing.md`).
- Removing redundant phrasing (e.g., "about several minutes" to "several
minutes" in `DeepSeek-V3.1.md`).
- Clarifying evaluation methods (e.g., specifying AISBench in
`DeepSeek-V4-Flash.md`).
- Removing outdated time-relative references (e.g., "Last month" in
`GLM4.x.md`).
- Fixing duplicate references to the vLLM Benchmark in
`Qwen3-Omni-30B-A3B-Thinking.md`.

### Does this PR introduce _any_ user-facing change?
No, this PR only contains documentation updates.

### How was this patch tested?
No testing is required as these are documentation-only changes.


- vLLM version: v0.26.0
- vLLM main:
vllm-project/vllm@d02df74

---------

Signed-off-by: herizhen <1270637059@qq.com>
Signed-off-by: herizhen <59841270+herizhen@users.noreply.github.com>

Author: herizhen

docs/source/developer_guide/contribution/testing.md

@@ -57,7 +57,7 @@ The fastest way to set up a test environment is to use the main branch's contain
     python3 -m pip install -r requirements-dev.txt
     ```
 
-=== "Single card"
+=== "Single-card"
 
     ```bash
 
@@ -95,7 +95,7 @@ The fastest way to set up a test environment is to use the main branch's contain
     pip install -r requirements-dev.txt
     ```
 
-=== "Multi cards"
+=== "Multi-cards"
 
     ```bash
     # Update the vllm-ascend image

docs/source/tutorials/models/DeepSeek-V3.1.md

@@ -914,7 +914,7 @@ Take the `serve` as an example. Run the code as follows.
 vllm bench serve --model /weights/DeepSeek-V3.1-w8a8-mtp-QuaRot  --dataset-name random --random-input 1024 --num-prompts 200 --request-rate 1 --save-result --result-dir ./
 ```
 
-After about several minutes, you can get the performance evaluation result.
+After several minutes, you can get the performance evaluation result.
 
 ## 9 Performance Tuning
 

docs/source/tutorials/models/DeepSeek-V4-Flash.md

@@ -906,7 +906,7 @@ The service returns HTTP 200 OK with a JSON response containing the `choices` fi
 
 ## 7 Accuracy Evaluation
 
-Here are two accuracy evaluation methods.
+Here is the accuracy evaluation method using AISBench.
 
 ### Using AISBench
 

docs/source/tutorials/models/GLM4.x.md

@@ -22,7 +22,7 @@ Refer to [feature guide](../../user_guide/feature_guide/index.md) to get the fea
 - `GLM-4.6`(BF16 version): [Download model weight](https://www.modelscope.cn/models/ZhipuAI/GLM-4.6).
 - `GLM-4.7`(BF16 version): [Download model weight](https://www.modelscope.cn/models/ZhipuAI/GLM-4.7).
 - `GLM-4.5-w8a8-with-float-mtp`(Quantized version with mtp): [Download model weight](https://modelers.cn/models/Modelers_Park/GLM-4.5-w8a8).
-- `GLM-4.6-w8a8`(Quantized version without mtp): [Download model weight](https://modelers.cn/models/Modelers_Park/GLM-4.6-w8a8). Because vllm does not support GLM4.6 mtp in October, we do not provide an mtp version. Last month, it was supported; you can use the following quantization scheme to add mtp weights to the quantized weights.
+- `GLM-4.6-w8a8`(Quantized version without mtp): [Download model weight](https://modelers.cn/models/Modelers_Park/GLM-4.6-w8a8). Because vllm does not support GLM4.6 mtp in October, we do not provide an mtp version. Since it is now supported, you can use the following quantization scheme to add mtp weights to the quantized weights.
 - `GLM-4.7-w8a8-with-float-mtp`(Quantized version without mtp): [Download model weight](https://modelscope.cn/models/Eco-Tech/GLM-4.7-W8A8-floatmtp).
 - `Method of Quantization`: [quantization scheme](https://ai.gitcode.com/Ascend-SACT/GLM-4.5-w8a8). You can use these methods to quantize the model.
 

docs/source/tutorials/models/Qwen3-Next.md

@@ -4,7 +4,7 @@
 
 The Qwen3-Next model is a sparse MoE (Mixture of Experts) model with high sparsity. Compared to the MoE architecture of Qwen3, it has introduced key improvements in aspects such as the hybrid attention mechanism and multi-token prediction mechanism, enhancing the training and inference efficiency of the model under long contexts and large total parameter scales.
 
-This document will present the core verification steps of the model, including supported features, environment preparation, as well as accuracy and performance evaluation. Qwen3 Next is currently using Triton Ascend, which is in the experimental phase. In subsequent versions, its performance related to stability and accuracy may change, and performance will be continuously optimized.
+This document will present the core verification steps of the model, including supported features, environment preparation, as well as accuracy and performance evaluation. Qwen3-Next is currently using Triton Ascend, which is in the experimental phase. In subsequent versions, its performance related to stability and accuracy may change, and performance will be continuously optimized.
 
 The `Qwen3-Next` model is first supported in `vllm-ascend:v0.10.2rc1` and can stably run in v0.16.0 and later version.
 
@@ -69,7 +69,7 @@ docker run --rm \
 -it $IMAGE bash
 ```
 
-The Qwen3 Next is using [Triton Ascend](https://gitee.com/ascend/triton-ascend) which is currently experimental. In future versions, there may be behavioral changes related to stability, accuracy, and performance improvement.
+The Qwen3-Next is using [Triton Ascend](https://gitee.com/ascend/triton-ascend) which is currently experimental. In future versions, there may be behavioral changes related to stability, accuracy, and performance improvement.
 
 **Installation Verification:**
 
@@ -158,7 +158,7 @@ curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/jso
 }'
 ```
 
-Expected Result:
+Expected result:
 
 The service returns HTTP 200 OK with a JSON response containing the `choices` field. Example output (content truncated for brevity):
 

docs/source/tutorials/models/Qwen3-Omni-30B-A3B-Thinking.md

@@ -379,7 +379,6 @@ As an example, take the `gsm8k` `omni_bench` `bbh` dataset as a test dataset, an
 ### Using vLLM Benchmark
 
 Run performance evaluation of `Qwen3-Omni-30B-A3B-Thinking` as an example.
-Refer to vllm benchmark for more details.
 Refer to [vLLM Benchmark](https://docs.vllm.ai/en/latest/benchmarking/) for more details.
 
 There are three `vllm bench` subcommands:

docs/source/tutorials/models/gpt-oss-120b.md

@@ -65,7 +65,7 @@ docker run --rm \
     -it $IMAGE bash
 ```
 
-The default workdir is `/workspace`, vLLM and vLLM Ascend code are placed in `/vllm-workspace` and installed in [development mode](https://setuptools.pypa.io/en/latest/userguide/development_mode.html) (`pip install -e`) to help developer immediately take place changes without requiring a new installation.
+The default workdir is `/workspace`, vLLM and vLLM Ascend code are placed in `/vllm-workspace` and installed in [development mode](https://setuptools.pypa.io/en/latest/userguide/development_mode.html) (`pip install -e`) to help developers apply changes immediately without requiring a new installation.
 
 In addition, if you don't want to use the docker image as above, you can also build all from source:
 

docs/source/user_guide/feature_guide/quantization.md

@@ -104,7 +104,7 @@ The quantization types currently supported by LLM-Compressor can be viewed in th
 
 ## Running Quantized Models
 
-Once you have a quantized model which is generated by **ModelSlim**, you can use vLLM Ascend for inference by specifying the `--quantization ascend` parameter to enable quantization features, while for models quantized by **LLM-Compressor**, do not need to add this parameter.
+Once you have a quantized model which is generated by **ModelSlim**, you can use vLLM Ascend for inference by specifying the `--quantization ascend` parameter to enable quantization features, while for models quantized by **LLM-Compressor**, it is not necessary to add this parameter.
 
 ### Offline Inference