Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -197,7 +197,7 @@ Run Ianvs for benchmarking:
```bash
cd /ianvs
export DASHSCOPE_API_KEY="your_api_key_here"
ianvs -f examples/Cloud_Robotics/cloud-edge-collaborative-inference-bench/perception-reasoning/benchmarkingjob.yaml
python benchmarking.py -f examples/Cloud_Robotics/cloud-edge-collaborative-inference-bench/perception-reasoning/benchmarkingjob.yaml
```
**Note**: Replace `"your_api_key_here"` with your actual Dashscope API key.

Expand Down
2 changes: 1 addition & 1 deletion examples/GovDoc2Poster/singletask_learning_bench/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -138,7 +138,7 @@ cd /home/linux/Desktop/ianvs
### Step 3: Run the System

```bash
ianvs -f examples/GovDoc2Poster/singletask_learning_bench/testalgorithms/gen/government_data_source.yaml
python benchmarking.py -f examples/GovDoc2Poster/singletask_learning_bench/testalgorithms/gen/government_data_source.yaml
```

✅ Done! The system will automatically parse the government documents from the dataset and generate visual posters.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ Next, download pretrained model via [[google]](https://drive.google.com/file/d/1
We are now ready to run the ianvs for benchmarking pedestrian tracking on the MOT17 dataset.

```python
ianvs -f ./examples/MOT17/multiedge_inference_bench/pedestrian_tracking/tracking_job.yaml
python benchmarking.py -f ./examples/MOT17/multiedge_inference_bench/pedestrian_tracking/tracking_job.yaml

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The code block on line 49 is marked with python syntax highlighting, but the command inside is a shell/bash command. Please consider changing the language specifier on line 49 to bash or shell for correct syntax highlighting.

```

The benchmarking process takes a few minutes and varies depending on devices.
Expand Down Expand Up @@ -78,7 +78,7 @@ Next, download pretrained model via [[google]](https://drive.google.com/drive/fo
We are now ready to run the ianvs for benchmarking pedestrian re-identification on the MOT17 dataset.

```python
ianvs -f ./examples/MOT17/multiedge_inference_bench/pedestrian_tracking/reid_job.yaml
python benchmarking.py -f ./examples/MOT17/multiedge_inference_bench/pedestrian_tracking/reid_job.yaml

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The code block on line 80 is marked with python syntax highlighting, but the command inside is a shell/bash command. Please consider changing the language specifier on line 80 to bash or shell for correct syntax highlighting.

```

The benchmarking process takes a few minutes and varies depending on devices.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -115,7 +115,7 @@ export CLOUD_API_KEY="your_cloud_model_api_key"

3. Run benchmark:
```bash
ianvs -f benchmarkingjob.yaml
python benchmarking.py -f benchmarkingjob.yaml
```

## Evaluation Methods
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -115,7 +115,7 @@ We are now ready to run the ianvs for benchmarking.

``` shell
cd /ianvs/project
ianvs -f examples/bdd/lifelong_learning_bench/curb-detection/benchmarkingjob.yaml
python benchmarking.py -f examples/bdd/lifelong_learning_bench/curb-detection/benchmarkingjob.yaml
```

Finally, the user can check the result of benchmarking on the console and also in the output path(
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -80,7 +80,7 @@ We are now ready to run the ianvs for benchmarking.

``` shell
cd /ianvs/project/ianvs
ianvs -f examples/cityscapes-synthia/lifelong_learning_bench/curb-detection/benchmarkingjob.yaml
python benchmarking.py -f examples/cityscapes-synthia/lifelong_learning_bench/curb-detection/benchmarkingjob.yaml
```

Finally, the user can check the result of benchmarking on the console and also in the output path(
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -86,7 +86,7 @@ We are now ready to run the ianvs for benchmarking.

``` shell
cd /ianvs/project/ianvs
ianvs -f examples/cityscapes-synthia/lifelong_learning_bench/semantic-segmentation/benchmarkingjob-smalltest.yaml
python benchmarking.py -f examples/cityscapes-synthia/lifelong_learning_bench/semantic-segmentation/benchmarkingjob-smalltest.yaml
```

Finally, the user can check the result of benchmarking on the console and also in the output path(
Expand Down
4 changes: 2 additions & 2 deletions examples/cloud-edge-collaborative-inference-for-llm/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -141,7 +141,7 @@ export OPENAI_API_KEY=sk_xxxxxxxx

6. Run the Ianvs benchmark:
```bash
ianvs -f examples/cloud-edge-collaborative-inference-for-llm/benchmarkingjob.yaml
python benchmarking.py -f examples/cloud-edge-collaborative-inference-for-llm/benchmarkingjob.yaml
```

*Note: To help you get results quickly, we have provided a workspace folder with cached results for `Qwen/Qwen2.5-1.5B-Instruct`, `Qwen/Qwen2.5-3B-Instruct`,`Qwen/Qwen2.5-7B-Instruct` and `gpt-4o-mini`.*
Expand Down Expand Up @@ -352,7 +352,7 @@ You can download `workspace-mmlu` folder from [Ianvs-MMLU-5-shot](https://www.ka

Run the following command:

`ianvs -f examples/cloud-edge-collaborative-inference-for-llm/benchmarkingjob.yaml`
`python benchmarking.py -f examples/cloud-edge-collaborative-inference-for-llm/benchmarkingjob.yaml`

After the process finished, you will see output like this:

Expand Down
4 changes: 2 additions & 2 deletions examples/cloud-edge-speculative-decoding-benchmark/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -182,13 +182,13 @@ Common options include:
Run the `AR` benchmark:

```bash
ianvs -f examples/cloud-edge-speculative-decoding-benchmark/benchmarkingjob.yaml
python benchmarking.py -f examples/cloud-edge-speculative-decoding-benchmark/benchmarkingjob.yaml
```

Run the `Block` benchmark:

```bash
ianvs -f examples/cloud-edge-speculative-decoding-benchmark/benchmarkingjob_block.yaml
python benchmarking.py -f examples/cloud-edge-speculative-decoding-benchmark/benchmarkingjob_block.yaml
```

Benchmark outputs are written under the workspace configured in each benchmarking job file:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -310,7 +310,7 @@ Run the following command:

```
cd ianvs
ianvs -f /examples/cloud_VLA_finetune/singletask_learning_bench/benchmarkingjob.yaml
python benchmarking.py -f /examples/cloud_VLA_finetune/singletask_learning_bench/benchmarkingjob.yaml

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The path to the benchmarking job YAML file has a leading slash (/examples/...), which makes it an absolute path. Since the user just ran cd ianvs to enter the repository root, this should be a relative path (examples/...) so that the file can be correctly located relative to the current working directory.

Suggested change
python benchmarking.py -f /examples/cloud_VLA_finetune/singletask_learning_bench/benchmarkingjob.yaml
python benchmarking.py -f examples/cloud_VLA_finetune/singletask_learning_bench/benchmarkingjob.yaml

```

After the process finished, you will see output like this:
Expand Down
2 changes: 1 addition & 1 deletion examples/federated-llm/fedllm-peft/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -246,7 +246,7 @@ Each line should be a valid JSON object with at least two fields representing th
Execute the federated LLM fine-tuning benchmark:

```bash
ianvs -f ./examples/federated-llm/fedllm-peft/benchmarkingjob.yaml
python benchmarking.py -f ./examples/federated-llm/fedllm-peft/benchmarkingjob.yaml
```

**Important**: Please change the path to `benchmarkingjob.yaml` as per your setup.
Expand Down
4 changes: 2 additions & 2 deletions examples/government/singletask_learning_bench/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -97,8 +97,8 @@ Or you can replace the file in `yourpath/anaconda3/envs/ianvs/lib/python3.x/site

### Objective

`ianvs -f examples/government/singletask_learning_bench/objective/benchmarkingjob.yaml`
`python benchmarking.py -f examples/government/singletask_learning_bench/objective/benchmarkingjob.yaml`

### Subjective

`ianvs -f examples/government/singletask_learning_bench/subjective/benchmarkingjob.yaml`
`python benchmarking.py -f examples/government/singletask_learning_bench/subjective/benchmarkingjob.yaml`
2 changes: 1 addition & 1 deletion examples/government_rag/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,7 @@ For each region's evaluation, we have four experimental designs (Type 1, 2, 3, 4

2. Run the test:
```bash
ianvs -f examples/government_rag/singletask_learning_bench/benchmarkingjob.yaml
python benchmarking.py -f examples/government_rag/singletask_learning_bench/benchmarkingjob.yaml
```

## Test Results
Expand Down
4 changes: 2 additions & 2 deletions examples/imagenet/multiedge_inference_bench/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ Next, download pretrained model via [[huggingface]](https://huggingface.co/optim
We are now ready to run the ianvs for benchmarking image classification for high mobility scenarios on the ImageNet dataset.

```python
ianvs -f ./examples/imagenet/multiedge_inference_bench/classification_job_manual.yaml
python benchmarking.py -f ./examples/imagenet/multiedge_inference_bench/classification_job_manual.yaml

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The code block on line 46 is marked with python syntax highlighting, but the command inside is a shell/bash command. Please consider changing the language specifier on line 46 to bash or shell for correct syntax highlighting.

```

The benchmarking process takes a few minutes and varies depending on devices.
Expand Down Expand Up @@ -75,7 +75,7 @@ Then you will find a profiler_results.yml file in the <Ianvs_HOME>/examples/imag

Then you can run the following command to perform benchmarking:
```shell
ianvs -f ./examples/imagenet/multiedge_inference_bench/classification_job_auto.yaml
python benchmarking.py -f ./examples/imagenet/multiedge_inference_bench/classification_job_auto.yaml
```

After running, you will see the profit from the automatic method compared with the manual method.
Expand Down
2 changes: 1 addition & 1 deletion examples/industrialEI/pose-estimation-llio/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -140,7 +140,7 @@ pose-estimation-llio/

5. **Run Benchmarking**:
```bash
ianvs -f examples/industrialEI/pose-estimation-llio/benchmarkingjob.yaml
python benchmarking.py -f examples/industrialEI/pose-estimation-llio/benchmarkingjob.yaml
```

## Configuration
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -224,7 +224,7 @@ Execute the benchmark:

```shell
cd /ianvs
ianvs -f examples/industrialEI/single_task_learning_bench/deformable_assembly/benchmarkingjob.yaml
python benchmarking.py -f examples/industrialEI/single_task_learning_bench/deformable_assembly/benchmarkingjob.yaml
```


Expand Down
2 changes: 1 addition & 1 deletion examples/llm-agent/singletask_learning_bench/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ pip install -r examples/llm-agent/singletask_learning_bench/requirements.txt
# pipeline works.

# 5. Run the benchmark
ianvs -f examples/llm-agent/singletask_learning_bench/benchmarkingjob.yaml
python benchmarking.py -f examples/llm-agent/singletask_learning_bench/benchmarkingjob.yaml
```

First run is slow because HuggingFace downloads `Langboat/bloom-1b4-zh` (~3 GB) into `~/.cache/huggingface`. Subsequent runs use the cache and start immediately.
Expand Down
4 changes: 2 additions & 2 deletions examples/llm-edge-benchmark-suite/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -31,11 +31,11 @@ python setup.py install


```shell
ianvs -f examples/llm-edge-benchmark-suite/single_task_bench/benchmarkingjob.yaml
python benchmarking.py -f examples/llm-edge-benchmark-suite/single_task_bench/benchmarkingjob.yaml
```


```shell
ianvs -f examples/llm-edge-benchmark-suite/single_task_bench_with_compression/benchmarkingjob.yaml
python benchmarking.py -f examples/llm-edge-benchmark-suite/single_task_bench_with_compression/benchmarkingjob.yaml
```

Original file line number Diff line number Diff line change
Expand Up @@ -173,7 +173,7 @@ during pipeline execution.
From `$REPO_ROOT`:

```bash
ianvs -f examples/llm-edge-benchmark-suite/single_task_bench/benchmarkingjob.yaml
python benchmarking.py -f examples/llm-edge-benchmark-suite/single_task_bench/benchmarkingjob.yaml
```

Ianvs loads the configs, instantiates `LlamaCppModel`, streams inference over
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@ dataset:
Once all paths are absolute and the script is updated, execute the benchmark:

```bash
ianvs -f ianvs/examples/llm-edge-benchmark-suite/single_task_bench_with_compression/benchmarkingjob.yaml
python benchmarking.py -f ianvs/examples/llm-edge-benchmark-suite/single_task_bench_with_compression/benchmarkingjob.yaml

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The path contains an extra ianvs/ prefix (ianvs/examples/...). Since benchmarking.py is run from the root of the repository, the examples directory is directly accessible. Using ianvs/examples/... will result in a "file not found" error. Please use a relative path starting with examples/.

Suggested change
python benchmarking.py -f ianvs/examples/llm-edge-benchmark-suite/single_task_bench_with_compression/benchmarkingjob.yaml
python benchmarking.py -f examples/llm-edge-benchmark-suite/single_task_bench_with_compression/benchmarkingjob.yaml

```

### Expected Output
Expand Down
2 changes: 1 addition & 1 deletion examples/llm_simple_qa/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -70,7 +70,7 @@ Replace the file in `yourpath/anaconda3/envs/ianvs/lib/python3.x/site-packages/s

Run the following command:

`ianvs -f examples/llm/singletask_learning_bench/simple_qa/benchmarkingjob.yaml`
`python benchmarking.py -f examples/llm/singletask_learning_bench/simple_qa/benchmarkingjob.yaml`

## OpenCompass Evaluation

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,7 @@ We are now ready to run the ianvs for benchmarking.

``` shell
cd /ianvs/project
ianvs -f examples/robot-cityscapes-synthia/lifelong_learning_bench/semantic-segmentation/benchmarkingjob.yaml
python benchmarking.py -f examples/robot-cityscapes-synthia/lifelong_learning_bench/semantic-segmentation/benchmarkingjob.yaml
```

Finally, the user can check the result of benchmarking on the console and also in the output path(
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -130,7 +130,7 @@ To run the basic lifelong learning process:

```shell
cd /ianvs/project/ianvs
ianvs -f examples/robot/lifelong_learning_bench/semantic-segmentation/benchmarkingjob-simple.yaml
python benchmarking.py -f examples/robot/lifelong_learning_bench/semantic-segmentation/benchmarkingjob-simple.yaml
```

Finally, the user can check the result of benchmarking on the console and also in the output path(
Expand All @@ -148,7 +148,7 @@ To run the large vision model based cloud-edge collaboration process:

```shell
cd /ianvs/project/ianvs
ianvs -f examples/robot/lifelong_learning_bench/semantic-segmentation/benchmarkingjob-sam.yaml
python benchmarking.py -f examples/robot/lifelong_learning_bench/semantic-segmentation/benchmarkingjob-sam.yaml
```

Finally, the user can check the result of benchmarking on the console and also in the output path(
Expand Down
4 changes: 2 additions & 2 deletions examples/smart_coding/smart_coding_learning_bench/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -107,8 +107,8 @@ Or you can replace the file in `yourpath/anaconda3/envs/ianvs/lib/python3.x/site

### Comment

`ianvs -f examples/smart_coding/smart_coding_learning_bench/comment/benchmarkingjob.yaml`
`python benchmarking.py -f examples/smart_coding/smart_coding_learning_bench/comment/benchmarkingjob.yaml`

### Issue

`ianvs -f examples/smart_coding/smart_coding_learning_bench/issue/benchmarkingjob.yaml`
`python benchmarking.py -f examples/smart_coding/smart_coding_learning_bench/issue/benchmarkingjob.yaml`