Skip to content

Fix indentations and consistency in benchmark.md #557

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
hami-robot merged 1 commit into from
Jul 6, 2026
Merged

Fix indentations and consistency in benchmark.md #557

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 19 additions & 19 deletions docs/userguide/benchmark.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,11 +17,11 @@ Three instances from the vLLM benchmark were used to evaluate vGPU-device-plugin

## Test Instances

| Instance | Description |
| --------------- | :---------------------------------------------------: |
| Native | k8s + nvidia k8s-device-plugin |
| Opensource_v280 | k8s + vGPU k8s-device-plugin, opensource version v280 |
| Opensource_v290 | k8s + vGPU k8s-device-plugin, opensource version v290 |
| Instance | Description |
| --------------- | :----------------------------------------------------------: |
| Native | Kubernetes + NVIDIA k8s-device-plugin |
| Opensource_v280 | Kubernetes + vGPU k8s-device-plugin, opensource version v280 |
| Opensource_v290 | Kubernetes + vGPU k8s-device-plugin, opensource version v290 |

## Test Cases

Expand All @@ -44,23 +44,23 @@ Three instances from the vLLM benchmark were used to evaluate vGPU-device-plugin

1. Build the benchmark images:

```bash
cd benchmarks/ai-benchmark
sh build.sh
```
```bash
cd benchmarks/ai-benchmark
sh build.sh
```

1. Run the benchmark job:

```bash
kubectl apply -f benchmarks/deployments/job-on-nvidia-device-plugin.yml
kubectl apply -f benchmarks/deployments/job-on-hami.yml
```
```bash
kubectl apply -f benchmarks/deployments/job-on-nvidia-device-plugin.yml
kubectl apply -f benchmarks/deployments/job-on-hami.yml
```

1. View the results:

```bash
kubectl cp <pod-name>:/results ./results
python3 benchmarks/ai-benchmark/gen_report.py \
--dataset native ./results/bench_native.jsonl \
--dataset hami ./results/bench_hami.jsonl
```
```bash
kubectl cp <pod-name>:/results ./results
python3 benchmarks/ai-benchmark/gen_report.py \
--dataset native ./results/bench_native.jsonl \
--dataset hami ./results/bench_hami.jsonl
```
40 changes: 20 additions & 20 deletions i18n/zh/docusaurus-plugin-content-docs/current/userguide/benchmark.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,11 +17,11 @@ sidebar_label: 性能测试

## 测试实例

| 测试名称 | 测试用例 |
| --------------- | :-----------------------------------------: |
| Native | k8s + nvidia 官方 k8s-device-plugin |
| Opensource_v280 | k8s + vGPU k8s-device-plugin，开源版本 v280 |
| Opensource_v290 | k8s + vGPU k8s-device-plugin，开源版本 v290 |
| 测试名称 | 测试用例 |
| --------------- | :------------------------------------------------: |
| Native | Kubernetes + NVIDIA 官方 k8s-device-plugin |
| Opensource_v280 | Kubernetes + vGPU k8s-device-plugin，开源版本 v280 |
| Opensource_v290 | Kubernetes + vGPU k8s-device-plugin，开源版本 v290 |

## 测试内容

Expand All @@ -42,25 +42,25 @@ sidebar_label: 性能测试

1. 安装 k8s-vGPU-scheduler，并配置相应的参数。

2. 构建 benchmark 镜像：
1. 构建 benchmark 镜像：

```bash
cd benchmarks/ai-benchmark
sh build.sh
```
```bash
cd benchmarks/ai-benchmark
sh build.sh
```

1. 运行 benchmark 任务：

```bash
kubectl apply -f benchmarks/deployments/job-on-nvidia-device-plugin.yml
kubectl apply -f benchmarks/deployments/job-on-hami.yml
```
```bash
kubectl apply -f benchmarks/deployments/job-on-nvidia-device-plugin.yml
kubectl apply -f benchmarks/deployments/job-on-hami.yml
```

1. 查看结果：

```bash
kubectl cp <pod-name>:/results ./results
python3 benchmarks/ai-benchmark/gen_report.py \
--dataset native ./results/bench_native.jsonl \
--dataset hami ./results/bench_hami.jsonl
```
```bash
kubectl cp <pod-name>:/results ./results
python3 benchmarks/ai-benchmark/gen_report.py \
--dataset native ./results/bench_native.jsonl \
--dataset hami ./results/bench_hami.jsonl
```
36 changes: 18 additions & 18 deletions i18n/zh/docusaurus-plugin-content-docs/version-v2.9.0/userguide/benchmark.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,9 +19,9 @@ sidebar_label: 性能测试

| 测试名称 | 测试用例 |
| --------------- | :-----------------------------------------: |
| Native | k8s + nvidia 官方 k8s-device-plugin |
| Opensource_v280 | k8s + VGPU k8s-device-plugin，开源版本 v280 |
| Opensource_v290 | k8s + VGPU k8s-device-plugin，开源版本 v290 |
| Native | Kubernetes + NVIDIA 官方 k8s-device-plugin |
| Opensource_v280 | Kubernetes + VGPU k8s-device-plugin，开源版本 v280 |
| Opensource_v290 | Kubernetes + VGPU k8s-device-plugin，开源版本 v290 |

## 测试内容

Expand All @@ -42,25 +42,25 @@ sidebar_label: 性能测试

1. 安装 k8s-vGPU-scheduler，并配置相应的参数。

2. 构建 benchmark 镜像：
1. 构建 benchmark 镜像：

```bash
cd benchmarks/ai-benchmark
sh build.sh
```
```bash
cd benchmarks/ai-benchmark
sh build.sh
```

1. 运行 benchmark 任务：

```bash
kubectl apply -f benchmarks/deployments/job-on-nvidia-device-plugin.yml
kubectl apply -f benchmarks/deployments/job-on-hami.yml
```
```bash
kubectl apply -f benchmarks/deployments/job-on-nvidia-device-plugin.yml
kubectl apply -f benchmarks/deployments/job-on-hami.yml
```

1. 查看结果：

```bash
kubectl cp <pod-name>:/results ./results
python3 benchmarks/ai-benchmark/gen_report.py \
--dataset native ./results/bench_native.jsonl \
--dataset hami ./results/bench_hami.jsonl
```
```bash
kubectl cp <pod-name>:/results ./results
python3 benchmarks/ai-benchmark/gen_report.py \
--dataset native ./results/bench_native.jsonl \
--dataset hami ./results/bench_hami.jsonl
```