You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
[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>
Copy file name to clipboardExpand all lines: docs/source/community/governance.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,7 +2,7 @@
2
2
3
3
## Mission
4
4
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.
6
6
7
7
## Principles
8
8
@@ -18,7 +18,7 @@ vLLM Ascend is an open-source project under the vLLM community, where the author
18
18
19
19
**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.
20
20
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.
Copy file name to clipboardExpand all lines: docs/source/community/issue-workflow-guidelines.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
# Issue Workflow Guidelines
2
2
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.
[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.
6
6
7
7
LLaMA-Factory users need to evaluate the model and perform inference after fine-tuning.
8
8
9
-
**Business challenge**
9
+
## Business challenge
10
10
11
11
LLaMA-Factory uses Transformers to perform inference on Ascend NPUs, but the speed is slow.
12
12
13
-
**Benefits with vLLM Ascend**
13
+
## Benefits with vLLM Ascend
14
14
15
15
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.
16
16
17
-
**Learn more**
17
+
## Learn more
18
18
19
19
For more details about LLaMA-Factory, please refer to the [official documentation](https://llamafactory.readthedocs.io/en/latest/index.html).
Copy file name to clipboardExpand all lines: docs/source/developer_guide/Design_Documents/KV_Cache_Pool_Guide.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -86,6 +86,6 @@ The KV Connector methods that need to be implemented can be categorized into sch
86
86
87
87
## Limitations
88
88
89
-
1. Currently, MooncakeStore for vLLM-Ascend only supports DRAM as the storage for KV Cache pool.
89
+
1. Currently, MooncakeStore for vLLMAscend only supports DRAM as the storage for KV Cache Pool.
90
90
91
91
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).
Copy file name to clipboardExpand all lines: docs/source/developer_guide/Design_Documents/npugraph_ex.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -44,7 +44,7 @@ register_replacement(search_fn, replace_fn, example_inputs, trace_fn=fwd_only, e
44
44
|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|
45
45
|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|
Copy file name to clipboardExpand all lines: docs/source/developer_guide/Design_Documents/patch.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -25,11 +25,11 @@ vllm_ascend/
25
25
└── patch_yyy.py
26
26
```
27
27
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.
29
29
- 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.
30
30
- 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.
Copy file name to clipboardExpand all lines: docs/source/developer_guide/contribution/e2e_ci_test.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -5,7 +5,7 @@ comment command, without running the full E2E test suite.
5
5
6
6
## Background
7
7
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
9
9
when a PR has `ready` label. This is expensive in CI resources
0 commit comments