Skip to content

Commit dd13a7f

Browse files
ella1107x60087760
andauthored
[Doc][Misc] Fix typos, grammar, and formatting in documentation (vllm-project#13082)
### What this PR does / why we need it? This PR addresses various typos, grammatical errors, and formatting inconsistencies across multiple documentation files (including governance, issue workflow, versioning policy, and developer guides) to improve overall readability and correctness. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? This is a documentation-only change. No runtime code changes were introduced. - vLLM version: v0.26.0 - vLLM main: vllm-project/vllm@d02df74 --------- Signed-off-by: x60087760 <xiechangxiu3@h-partners.com> Co-authored-by: x60087760 <xiechangxiu3@h-partners.com>
1 parent 13ed9f2 commit dd13a7f

14 files changed

Lines changed: 59 additions & 59 deletions

File tree

docs/source/community/governance.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22

33
## Mission
44

5-
As a vital component of vLLM, the vLLM Ascend project is dedicated to providing an easy, fast, and cheap LLM Serving for everyone on Ascend NPUs and to actively contributing to the enrichment of vLLM.
5+
As a vital component of vLLM, the vLLM Ascend project is dedicated to providing an easy, fast, and cheap LLM Serving for everyone on Ascend NPUs and to actively contribute to the enrichment of vLLM.
66

77
## Principles
88

@@ -18,7 +18,7 @@ vLLM Ascend is an open-source project under the vLLM community, where the author
1818

1919
**Requirements:** Complete at least 1 contribution. A contributor is someone who consistently and actively participates in a project, including but not limited to issue/review/commits/community involvement.
2020

21-
The contributor permissions are granted by the [vllm-project/vllm-ascend](https://github.com/vllm-project/vllm-ascend)'s repo `Triage` on GitHub, including repo read and clone, issue and PR management, facilitating efficient collaboration between community developers.
21+
Contributors are granted the `Triage` role in the [vllm-project/vllm-ascend](https://github.com/vllm-project/vllm-ascend) GitHub repository, which allows them to read and clone the repo, manage issues and PRs, and collaborate efficiently with community developers.
2222

2323
- Maintainer:
2424

docs/source/community/issue-workflow-guidelines.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# Issue Workflow Guidelines
22

3-
This document defines the standard lifecycle for Issues in the vLLM Ascend project — from creation through triage, active handling, and final closure. It establishes consistent label usage, owner assignment, and communication expectations to ensure smooth collaboration between contributors and maintainers.
3+
This document defines the standard lifecycle for [Issues](https://github.com/vllm-project/vllm-ascend/issues) in the vLLM Ascend project — from creation through triage, active handling, and final closure. It establishes consistent label usage, owner assignment, and communication expectations to ensure smooth collaboration between contributors and maintainers.
44

55
## 1. Label Categories
66

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,19 +1,19 @@
11
# LLaMA-Factory
22

3-
**Introduction**
3+
## Introduction
44

55
[LLaMA-Factory](https://github.com/hiyouga/LlamaFactory) is an easy-to-use and efficient platform for training and fine-tuning large language models. With LLaMA-Factory, you can fine-tune hundreds of pre-trained models locally without writing any code.
66

77
LLaMA-Factory users need to evaluate the model and perform inference after fine-tuning.
88

9-
**Business challenge**
9+
## Business challenge
1010

1111
LLaMA-Factory uses Transformers to perform inference on Ascend NPUs, but the speed is slow.
1212

13-
**Benefits with vLLM Ascend**
13+
## Benefits with vLLM Ascend
1414

1515
With the joint efforts of LLaMA-Factory and vLLM Ascend ([LLaMA-Factory#7739](https://github.com/hiyouga/LlamaFactory/pull/7739)), LLaMA-Factory has achieved significant performance gains during model inference. Benchmark results show that its inference speed is now up to 2× faster compared to the Transformers implementation.
1616

17-
**Learn more**
17+
## Learn more
1818

1919
For more details about LLaMA-Factory, please refer to the [official documentation](https://llamafactory.readthedocs.io/en/latest/index.html).

docs/source/community/versioning_policy.md

Lines changed: 29 additions & 29 deletions
Original file line numberDiff line numberDiff line change
@@ -29,35 +29,35 @@ The table below is the release compatibility matrix for vLLM Ascend release.
2929
| v0.20.2rc1 | v0.20.2 | >= 3.10, < 3.12 | 9.0.0 | 2.10.0 / 2.10.0 | 3.2.1 | v0.3.8.post1 |
3030
| v0.19.1rc1 | v0.19.1 | >= 3.10, < 3.12 | 8.5.1 | 2.9.0 / 2.9.0 | 3.2.0 | v0.3.8.post1 |
3131
| v0.18.0 | v0.18.0 | >= 3.10, < 3.12 | 8.5.1 | 2.9.0 / 2.9.0.post1+git4c901a4 | 3.2.0.dev20260322 | v0.3.9 |
32-
| v0.18.0rc1 | v0.18.0 | >= 3.10, < 3.12 | 8.5.1 | 2.9.0 / 2.9.0 | 3.2.0 | |
33-
| v0.17.0rc1 | v0.17.0 | >= 3.10, < 3.12 | 8.5.1 | 2.9.0 / 2.9.0 | 3.2.0 | |
34-
| v0.16.0rc1 | v0.16.0 | >= 3.10, < 3.12 | 8.5.1 | 2.9.0 / 2.9.0 | 3.2.0 | |
35-
| v0.15.0rc1 | v0.15.0 | >= 3.10, < 3.12 | 8.5.0 | 2.9.0 / 2.9.0 | 3.2.0 | |
36-
| v0.14.0rc1 | v0.14.1 | >= 3.10, < 3.12 | 8.5.0 | 2.9.0 / 2.9.0 | 3.2.0 | |
37-
| v0.13.0rc3 | v0.13.0 | >= 3.10, < 3.12 | 8.5.1 | 2.8.0 / 2.8.0.post2 | 3.2.0 | |
38-
| v0.13.0 | v0.13.0 | >= 3.10, < 3.12 | 8.5.0 | 2.8.0 / 2.8.0.post2 | 3.2.0 | |
39-
| v0.13.0rc2 | v0.13.0 | >= 3.10, < 3.12 | 8.5.0 | 2.8.0 / 2.8.0.post1 | 3.2.0 | |
40-
| v0.13.0rc1 | v0.13.0 | >= 3.10, < 3.12 | 8.3.RC2 | 2.8.0 / 2.8.0 | | |
41-
| v0.12.0rc1 | v0.12.0 | >= 3.10, < 3.12 | 8.3.RC2 | 2.8.0 / 2.8.0 | | |
42-
| v0.11.0 | v0.11.0 | >= 3.9, < 3.12 | 8.3.RC2 | 2.7.1 / 2.7.1.post1 | | |
43-
| v0.11.0rc3 | v0.11.0 | >= 3.9, < 3.12 | 8.3.RC2 | 2.7.1 / 2.7.1.post1 | | |
44-
| v0.11.0rc2 | v0.11.0 | >= 3.9, < 3.12 | 8.3.RC2 | 2.7.1 / 2.7.1 | | |
45-
| v0.11.0rc1 | v0.11.0 | >= 3.9, < 3.12 | 8.3.RC1 | 2.7.1 / 2.7.1 | | |
46-
| v0.11.0rc0 | v0.11.0rc3 | >= 3.9, < 3.12 | 8.2.RC1 | 2.7.1 / 2.7.1.dev20250724 | | |
47-
| v0.10.2rc1 | v0.10.2 | >= 3.9, < 3.12 | 8.2.RC1 | 2.7.1 / 2.7.1.dev20250724 | | |
48-
| v0.10.1rc1 | v0.10.1/v0.10.1.1 | >= 3.9, < 3.12 | 8.2.RC1 | 2.7.1 / 2.7.1.dev20250724 | | |
49-
| v0.10.0rc1 | v0.10.0 | >= 3.9, < 3.12 | 8.2.RC1 | 2.7.1 / 2.7.1.dev20250724 | | |
50-
| v0.9.2rc1 | v0.9.2 | >= 3.9, < 3.12 | 8.1.RC1 | 2.5.1 / 2.5.1.post1.dev20250619 | | |
51-
| v0.9.1 | v0.9.1 | >= 3.9, < 3.12 | 8.2.RC1 | 2.5.1 / 2.5.1.post1 | | |
52-
| v0.9.1rc3 | v0.9.1 | >= 3.9, < 3.12 | 8.2.RC1 | 2.5.1 / 2.5.1.post1 | | |
53-
| v0.9.1rc2 | v0.9.1 | >= 3.9, < 3.12 | 8.2.RC1 | 2.5.1 / 2.5.1.post1 | | |
54-
| v0.9.1rc1 | v0.9.1 | >= 3.9, < 3.12 | 8.1.RC1 | 2.5.1 / 2.5.1.post1.dev20250528 | | |
55-
| v0.9.0rc2 | v0.9.0 | >= 3.9, < 3.12 | 8.1.RC1 | 2.5.1 / 2.5.1 | | |
56-
| v0.9.0rc1 | v0.9.0 | >= 3.9, < 3.12 | 8.1.RC1 | 2.5.1 / 2.5.1 | | |
57-
| v0.8.5rc1 | v0.8.5.post1 | >= 3.9, < 3.12 | 8.1.RC1 | 2.5.1 / 2.5.1 | | |
58-
| v0.8.4rc2 | v0.8.4 | >= 3.9, < 3.12 | 8.0.0 | 2.5.1 / 2.5.1 | | |
59-
| v0.7.3.post1| v0.7.3 | >= 3.9, < 3.12 | 8.1.RC1 | 2.5.1 / 2.5.1 | | |
60-
| v0.7.3 | v0.7.3 | >= 3.9, < 3.12 | 8.1.RC1 | 2.5.1 / 2.5.1 | | |
32+
| v0.18.0rc1 | v0.18.0 | >= 3.10, < 3.12 | 8.5.1 | 2.9.0 / 2.9.0 | 3.2.0 | N/A |
33+
| v0.17.0rc1 | v0.17.0 | >= 3.10, < 3.12 | 8.5.1 | 2.9.0 / 2.9.0 | 3.2.0 | N/A |
34+
| v0.16.0rc1 | v0.16.0 | >= 3.10, < 3.12 | 8.5.1 | 2.9.0 / 2.9.0 | 3.2.0 | N/A |
35+
| v0.15.0rc1 | v0.15.0 | >= 3.10, < 3.12 | 8.5.0 | 2.9.0 / 2.9.0 | 3.2.0 | N/A |
36+
| v0.14.0rc1 | v0.14.1 | >= 3.10, < 3.12 | 8.5.0 | 2.9.0 / 2.9.0 | 3.2.0 | N/A |
37+
| v0.13.0rc3 | v0.13.0 | >= 3.10, < 3.12 | 8.5.1 | 2.8.0 / 2.8.0.post2 | 3.2.0 | N/A |
38+
| v0.13.0 | v0.13.0 | >= 3.10, < 3.12 | 8.5.0 | 2.8.0 / 2.8.0.post2 | 3.2.0 | N/A |
39+
| v0.13.0rc2 | v0.13.0 | >= 3.10, < 3.12 | 8.5.0 | 2.8.0 / 2.8.0.post1 | 3.2.0 | N/A |
40+
| v0.13.0rc1 | v0.13.0 | >= 3.10, < 3.12 | 8.3.RC2 | 2.8.0 / 2.8.0 | N/A | N/A |
41+
| v0.12.0rc1 | v0.12.0 | >= 3.10, < 3.12 | 8.3.RC2 | 2.8.0 / 2.8.0 | N/A | N/A |
42+
| v0.11.0 | v0.11.0 | >= 3.9, < 3.12 | 8.3.RC2 | 2.7.1 / 2.7.1.post1 | N/A | N/A |
43+
| v0.11.0rc3 | v0.11.0 | >= 3.9, < 3.12 | 8.3.RC2 | 2.7.1 / 2.7.1.post1 | N/A | N/A |
44+
| v0.11.0rc2 | v0.11.0 | >= 3.9, < 3.12 | 8.3.RC2 | 2.7.1 / 2.7.1 | N/A | N/A |
45+
| v0.11.0rc1 | v0.11.0 | >= 3.9, < 3.12 | 8.3.RC1 | 2.7.1 / 2.7.1 | N/A | N/A |
46+
| v0.11.0rc0 | v0.11.0rc3 | >= 3.9, < 3.12 | 8.2.RC1 | 2.7.1 / 2.7.1.dev20250724 | N/A | N/A |
47+
| v0.10.2rc1 | v0.10.2 | >= 3.9, < 3.12 | 8.2.RC1 | 2.7.1 / 2.7.1.dev20250724 | N/A | N/A |
48+
| v0.10.1rc1 | v0.10.1/v0.10.1.1 | >= 3.9, < 3.12 | 8.2.RC1 | 2.7.1 / 2.7.1.dev20250724 | N/A | N/A |
49+
| v0.10.0rc1 | v0.10.0 | >= 3.9, < 3.12 | 8.2.RC1 | 2.7.1 / 2.7.1.dev20250724 | N/A | N/A |
50+
| v0.9.2rc1 | v0.9.2 | >= 3.9, < 3.12 | 8.1.RC1 | 2.5.1 / 2.5.1.post1.dev20250619 | N/A | N/A |
51+
| v0.9.1 | v0.9.1 | >= 3.9, < 3.12 | 8.2.RC1 | 2.5.1 / 2.5.1.post1 | N/A | N/A |
52+
| v0.9.1rc3 | v0.9.1 | >= 3.9, < 3.12 | 8.2.RC1 | 2.5.1 / 2.5.1.post1 | N/A | N/A |
53+
| v0.9.1rc2 | v0.9.1 | >= 3.9, < 3.12 | 8.2.RC1 | 2.5.1 / 2.5.1.post1 | N/A | N/A |
54+
| v0.9.1rc1 | v0.9.1 | >= 3.9, < 3.12 | 8.1.RC1 | 2.5.1 / 2.5.1.post1.dev20250528 | N/A | N/A |
55+
| v0.9.0rc2 | v0.9.0 | >= 3.9, < 3.12 | 8.1.RC1 | 2.5.1 / 2.5.1 | N/A | N/A |
56+
| v0.9.0rc1 | v0.9.0 | >= 3.9, < 3.12 | 8.1.RC1 | 2.5.1 / 2.5.1 | N/A | N/A |
57+
| v0.8.5rc1 | v0.8.5.post1 | >= 3.9, < 3.12 | 8.1.RC1 | 2.5.1 / 2.5.1 | N/A | N/A |
58+
| v0.8.4rc2 | v0.8.4 | >= 3.9, < 3.12 | 8.0.0 | 2.5.1 / 2.5.1 | N/A | N/A |
59+
| v0.7.3.post1| v0.7.3 | >= 3.9, < 3.12 | 8.1.RC1 | 2.5.1 / 2.5.1 | N/A | N/A |
60+
| v0.7.3 | v0.7.3 | >= 3.9, < 3.12 | 8.1.RC1 | 2.5.1 / 2.5.1 | N/A | N/A |
6161

6262
!!! note
6363

docs/source/developer_guide/Design_Documents/KV_Cache_Pool_Guide.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -86,6 +86,6 @@ The KV Connector methods that need to be implemented can be categorized into sch
8686

8787
## Limitations
8888

89-
1. Currently, MooncakeStore for vLLM-Ascend only supports DRAM as the storage for KV Cache pool.
89+
1. Currently, MooncakeStore for vLLM Ascend only supports DRAM as the storage for KV Cache Pool.
9090

9191
2. For now, if we successfully looked up a key and found it exists, but failed to get it when calling KV Pool's get function, we just output a log indicating the get operation failed and keep going; hence, the accuracy of that specific request may be affected. We will handle this situation by falling back the request and re-compute everything assuming there's no prefix cache hit (or even better, revert only one block and keep using the Prefix Caches before that).

docs/source/developer_guide/Design_Documents/ModelRunner_prepare_inputs.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -9,7 +9,7 @@ Information required to perform model forward pass:
99

1010
The following diagram shows what we should prepare for model inference.
1111

12-
```shell
12+
```text
1313
+---------------+
1414
inputs --> | |
1515
| model | --> output

docs/source/developer_guide/Design_Documents/add_custom_aclnn_op.md

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -16,10 +16,10 @@ enable_custom_op()
1616

1717
## How to add a custom aclnn operation?
1818

19-
- Create a new operation folder under `csrc` directory.
20-
- Create `op_host` and `op_kernel` directories for host and kernel source code.
21-
- Add build options in `csrc/build_aclnn.sh` for supported SOC. Note that multiple ops should be separated with `;`, i.e. `CUSTOM_OPS="op1;op2;op3"`.
22-
- Bind aclnn operators to torch.ops._C_ascend module in `csrc/torch_binding.cpp`.
23-
- Write a meta implementation in `csrc/torch_binding_meta.cpp` for the op to be captured into the aclgraph.
19+
1. Create a new operation folder under `csrc` directory.
20+
2. Create `op_host` and `op_kernel` directories for host and kernel source code.
21+
3. Add build options in `csrc/build_aclnn.sh` for supported SOC. Note that multiple ops should be separated with `;`, i.e. `CUSTOM_OPS="op1;op2;op3"`.
22+
4. Bind aclnn operators to torch.ops._C_ascend module in `csrc/torch_binding.cpp`.
23+
5. Write a meta implementation in `csrc/torch_binding_meta.cpp` for the op to be captured into the aclgraph.
2424

2525
After a successful build of vllm-ascend, the custom aclnn operation can be invoked in Python code.

docs/source/developer_guide/Design_Documents/npugraph_ex.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -44,7 +44,7 @@ register_replacement(search_fn, replace_fn, example_inputs, trace_fn=fwd_only, e
4444
|extra_check|Input|Find the extra verification function after operator fusion. The function's input parameter must be a Match object from torch._inductor.pattern_matcher, and it is used for further custom checks on the matching result, such as checking whether the fused operators are on the same stream, checking the device type, checking the input shapes, and so on.|No|
4545
|search_fn_pattern|Input|A custom pattern object is generally unnecessary to provide. Its definition follows the rules of the native PyTorch MultiOutputPattern object. After passing this parameter, search_fn will no longer be used to match operator combinations; instead, this parameter will be used directly as the matching rule.|No|
4646

47-
Usage Example
47+
### Usage Example
4848

4949
```python
5050
import functools

docs/source/developer_guide/Design_Documents/patch.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -25,11 +25,11 @@ vllm_ascend/
2525
└── patch_yyy.py
2626
```
2727

28-
- **platform**: The patch code in this directory is for patching the code in vLLM main process. It's called by `vllm_ascend/platform::NPUPlatform::pre_register_and_update` very early when vLLM is initialized.
28+
- **platform**: The patch code in this directory is for patching the code in vLLM Main process. It's called by `vllm_ascend/platform::NPUPlatform::pre_register_and_update` very early when vLLM is initialized.
2929
- For online mode, vLLM process calls the platform patch in `vllm/vllm/engine/arg_utils.py::AsyncEngineArgs.add_cli_args` when parsing the CLI args.
3030
- For offline mode, vLLM process calls the platform patch in `vllm/vllm/engine/arg_utils.py::EngineArgs.create_engine_config` when parsing the input parameters.
31-
- **worker**: The patch code in this directory is for patching the code in vLLM worker process. It's called by `vllm_ascend/worker/worker::NPUWorker::__init__` when the vLLM worker process is initialized.
32-
- For both online and offline mode, vLLM engine core process calls the worker patch in `vllm/vllm/worker/worker_base.py::WorkerWrapperBase.init_worker` when initializing the worker process.
31+
- **worker**: The patch code in this directory is for patching the code in vLLM worker process. It's called by `vllm_ascend/worker/worker::NPUWorker::__init__` when the vLLM Worker process is initialized.
32+
- For both online and offline mode, vLLM EngineCore process calls the worker patch in `vllm/vllm/worker/worker_base.py::WorkerWrapperBase.init_worker` when initializing the worker process.
3333

3434
## How to write a patch
3535

docs/source/developer_guide/contribution/e2e_ci_test.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ comment command, without running the full E2E test suite.
55

66
## Background
77

8-
The `E2E-Full` workflow (`pr_test.yaml`) normally runs the complete E2E test suite
8+
The `E2E-Full` workflow ([`pr_test.yaml`](https://github.com/vllm-project/vllm-ascend/blob/main/.github/workflows/pr_test.yaml)) normally runs the complete E2E test suite
99
when a PR has `ready` label. This is expensive in CI resources
1010
and time.
1111

0 commit comments

Comments
 (0)