Skip to content

Commit bf3432a

Browse files
xieofxiehualxientrogh
authored
add Windows ML to AITK Profiling (#9177)
* add Windows ML * Apply suggestions from code review Co-authored-by: Nick Trogh <ntrogh@hotmail.com> * rename to use new name for images --------- Co-authored-by: hualxie <hualxie@microsoft.com> Co-authored-by: Nick Trogh <ntrogh@hotmail.com>
1 parent 071c35b commit bf3432a

8 files changed

Lines changed: 21 additions & 14 deletions

File tree

Lines changed: 3 additions & 0 deletions
Loading
Lines changed: 3 additions & 0 deletions
Loading

docs/intelligentapps/images/profiling/by-model-file.png

Lines changed: 0 additions & 3 deletions
This file was deleted.
Lines changed: 3 additions & 0 deletions
Loading

docs/intelligentapps/images/profiling/the-next-session.png

Lines changed: 0 additions & 3 deletions
This file was deleted.

docs/intelligentapps/overview.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -21,7 +21,7 @@ AI Toolkit offers seamless integration with popular AI models from providers lik
2121
| [Fine-tuning](/docs/intelligentapps/finetune) | Customize and adapt models for specific domains and requirements. Train models locally with GPU support or leverage Azure Container Apps for cloud-based fine-tuning. | ![Screenshot showing the Fine-tuning interface with model adaptation and training controls](./images/overview/fine-tune.png) |
2222
| [Model Conversion](/docs/intelligentapps/modelconversion) | Convert, quantize, and optimize machine learning models for local deployment. Transform models from Hugging Face and other sources to run efficiently on Windows with CPU, GPU, or NPU acceleration. | ![Screenshot showing the Model Conversion interface with tools for optimizing and transforming AI models](./images/overview/conversion.png) |
2323
| [Tracing](/docs/intelligentapps/tracing) | Monitor and analyze the performance of your AI applications. Collect and visualize trace data to gain insights into model behavior and performance. | ![Screenshot showing the Tracing interface with tools for monitoring AI applications](./images/overview/tracing.png) |
24-
| [Profiling](/docs/intelligentapps/profiling) | Diagnose the CPU, GPU, NPU resource usages of the process, ONNX model on different execution providers, and Windows ML events. | ![Screenshot showing the Profiling tool](./images/overview/profiling.png) |
24+
| [Profiling (Windows ML)](/docs/intelligentapps/profiling) | Diagnose the CPU, GPU, NPU resource usages of the process, ONNX model on different execution providers, and Windows Machine Learning events. | ![Screenshot showing the Profiling tool](./images/overview/profiling.png) |
2525

2626
## Who is AI Toolkit for?
2727

docs/intelligentapps/profiling.md

Lines changed: 10 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ In this article, you could learn how to start profiling and how to inspect the r
1919
In this mode, the profiling tool profiles the next app that is started and that is sending out Windows ML events.
2020
This option is ideal for testing a run-once app. In this case, you start profiling, then run the app, and the resource usages will begin showing up.
2121

22-
![Screenshot that shows how to start by the next session](./images/profiling/the-next-session.png)
22+
![Screenshot that shows how to start by the next session](./images/profiling/the-next-session-guide.png)
2323

2424
The tool starts profiling a newly started app. This means that for profiling a Python notebook, if the kernel is already running, you need to restart the kernel to begin profiling for it. Just starting a new notebook does not automatically start profiling.
2525

@@ -42,15 +42,19 @@ This option is ideal for profiling an app that is already running and you're una
4242

4343
## Profile an ONNX model
4444

45-
In this mode, the profiling tool starts profiling an ONNX model file on a target execution provider (EP) for a given duration. You can see the resource usage while it's running.
45+
In this mode, the profiling tool starts profiling an ONNX model file on a target execution provider (EP) or device policy for a given duration. You can see the resource usage while it's running.
4646

47-
This option is ideal for profiling an ONNX model on different EPs.
47+
This option is ideal for profiling an ONNX model on different EPs or device policies.
4848

49-
![Screenshot that shows how to start by model file](./images/profiling/by-model-file.png)
49+
![Screenshot that shows how to start by model file](./images/profiling/by-model-file-config.png)
5050

51-
After profiling, a report folder is created with logs and data.
51+
After profiling, a notification shows up to guide you to open or save the report.
5252

53-
![Screenshot that show the report data](./images/profiling/by-model-file-result.png)
53+
![Screenshot that shows the succeeded notification](./images/profiling/by-model-file-succeeded.png)
54+
55+
The report contains detailed profiling statistics and results for the ONNX model.
56+
57+
![Screenshot that shows the report data](./images/profiling/by-model-file-result.png)
5458

5559
## Resource Usages view
5660

docs/toc.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -397,7 +397,7 @@
397397
["Fine-tuning (Project Template)", "/docs/intelligentapps/finetune-legacy"],
398398
["Model Conversion", "/docs/intelligentapps/modelconversion"],
399399
["Tracing", "/docs/intelligentapps/tracing"],
400-
["Profiling", "/docs/intelligentapps/profiling"],
400+
["Profiling (Windows ML)", "/docs/intelligentapps/profiling"],
401401
["FAQ", "/docs/intelligentapps/faq"],
402402
["", "", {
403403
"name": "Reference",

0 commit comments

Comments
 (0)