Skip to content
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.

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

Update model analysis docs #974

Merged
merged 1 commit into from
Dec 27, 2024
Merged
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
592 changes: 592 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_base_v1_masked_lm.md

Large diffs are not rendered by default.

552 changes: 552 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_base_v1_token_cls.md

Large diffs are not rendered by default.

592 changes: 592 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_base_v2_masked_lm.md

Large diffs are not rendered by default.

552 changes: 552 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_base_v2_token_cls.md

Large diffs are not rendered by default.

592 changes: 592 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_large_v1_masked_lm.md

Large diffs are not rendered by default.

552 changes: 552 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_large_v1_token_cls.md

Large diffs are not rendered by default.

592 changes: 592 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_large_v2_masked_lm.md

Large diffs are not rendered by default.

552 changes: 552 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_large_v2_token_cls.md

Large diffs are not rendered by default.

542 changes: 542 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_xlarge_v1_masked_lm.md

Large diffs are not rendered by default.

502 changes: 502 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_xlarge_v1_token_cls.md

Large diffs are not rendered by default.

542 changes: 542 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_xlarge_v2_masked_lm.md

Large diffs are not rendered by default.

502 changes: 502 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_xlarge_v2_token_cls.md

Large diffs are not rendered by default.

592 changes: 592 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_xxlarge_v1_masked_lm.md

Large diffs are not rendered by default.

552 changes: 552 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_xxlarge_v1_token_cls.md

Large diffs are not rendered by default.

592 changes: 592 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_xxlarge_v2_masked_lm.md

Large diffs are not rendered by default.

552 changes: 552 additions & 0 deletions model_analysis_docs/Models/albert/pt_albert_xxlarge_v2_token_cls.md

Large diffs are not rendered by default.

412 changes: 412 additions & 0 deletions model_analysis_docs/Models/alexnet/pt_alexnet_torchhub.md

Large diffs are not rendered by default.

212 changes: 212 additions & 0 deletions model_analysis_docs/Models/autoencoder/pt_conv_ae.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,212 @@
<h1>Unique ops configuration and compiler support info</h1>
<table border="1" class="dataframe">
<thead>
<tr>
<th colspan="3" halign="left">Operation Details</th>
<th colspan="4" halign="left">Component Passing Check</th>
<th>Issues</th>
</tr>
<tr>
<th>Name</th>
<th>Operands</th>
<th>Arguments</th>
<th>Forge-Fe</th>
<th>MLIR</th>
<th>Metalium</th>
<th>N/A</th>
<th>Failure Reason</th>
</tr>
</thead>
<tbody>
<tr>
<td>Add</td>
<td>Operand(type=Activation, shape=(1, 16, 28, 28), dtype=float32)<br><div align='center'>X</div>Operand(type=Activation, shape=(16, 1, 1), dtype=float32)</td>
<td></td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
<tr>
<td>Add</td>
<td>Operand(type=Activation, shape=(1, 4, 14, 14), dtype=float32)<br><div align='center'>X</div>Operand(type=Activation, shape=(4, 1, 1), dtype=float32)</td>
<td></td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
<tr>
<td>Add</td>
<td>Operand(type=Activation, shape=(1, 16, 14, 14), dtype=float32)<br><div align='center'>X</div>Operand(type=Activation, shape=(16, 1, 1), dtype=float32)</td>
<td></td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
<tr>
<td>Add</td>
<td>Operand(type=Activation, shape=(1, 1, 28, 28), dtype=float32)<br><div align='center'>X</div>Operand(type=Activation, shape=(1, 1, 1), dtype=float32)</td>
<td></td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
<tr>
<td>Conv2d</td>
<td>Operand(type=Activation, shape=(1, 1, 28, 28), dtype=float32)<br><div align='center'>X</div>Operand(type=Parameter, shape=(16, 1, 3, 3), dtype=float32)</td>
<td>stride : [1, 1]<br>padding : [1, 1, 1, 1]<br>dilation : 1<br>groups : 1<br>channel_last : 0</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
<tr>
<td>Conv2d</td>
<td>Operand(type=Activation, shape=(1, 16, 14, 14), dtype=float32)<br><div align='center'>X</div>Operand(type=Parameter, shape=(4, 16, 3, 3), dtype=float32)</td>
<td>stride : [1, 1]<br>padding : [1, 1, 1, 1]<br>dilation : 1<br>groups : 1<br>channel_last : 0</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
<tr>
<td>Conv2dTranspose</td>
<td>Operand(type=Activation, shape=(1, 4, 7, 7), dtype=float32)<br><div align='center'>X</div>Operand(type=Parameter, shape=(4, 16, 2, 2), dtype=float32)</td>
<td>stride : 2<br>padding : 0<br>dilation : 1<br>groups : 1<br>channel_last : 0</td>
<td>&#x274C;</td>
<td>&#x274C;</td>
<td>&#x274C;</td>
<td></td>
<td>[FORGE][lower_to_mlir] RuntimeError Found Unsupported operations while lowering from TTForge to TTIR in forward graph</td>
</tr>
<tr>
<td>Conv2dTranspose</td>
<td>Operand(type=Activation, shape=(1, 16, 14, 14), dtype=float32)<br><div align='center'>X</div>Operand(type=Parameter, shape=(16, 1, 2, 2), dtype=float32)</td>
<td>stride : 2<br>padding : 0<br>dilation : 1<br>groups : 1<br>channel_last : 0</td>
<td>&#x274C;</td>
<td>&#x274C;</td>
<td>&#x274C;</td>
<td></td>
<td>[FORGE][lower_to_mlir] RuntimeError Found Unsupported operations while lowering from TTForge to TTIR in forward graph</td>
</tr>
<tr>
<td>MaxPool2d</td>
<td>Operand(type=Activation, shape=(1, 16, 28, 28), dtype=float32)</td>
<td>kernel_size : 2<br>stride : 2<br>padding : [0, 0, 0, 0]<br>dilation : 1<br>ceil_mode : False<br>max_pool_add_sub_surround : False<br>max_pool_add_sub_surround_value : 1.0<br>channel_last : 0</td>
<td>&#x2705;</td>
<td>&#x274C;</td>
<td>&#x274C;</td>
<td></td>
<td>[MLIR][ttnn.maxpool2d mlir pipeline] RuntimeError ttnn.max_pool2d currently only supports an input type of bfloat16 Failed to run MLIR compiler pass pipeline</td>
</tr>
<tr>
<td>MaxPool2d</td>
<td>Operand(type=Activation, shape=(1, 4, 14, 14), dtype=float32)</td>
<td>kernel_size : 2<br>stride : 2<br>padding : [0, 0, 0, 0]<br>dilation : 1<br>ceil_mode : False<br>max_pool_add_sub_surround : False<br>max_pool_add_sub_surround_value : 1.0<br>channel_last : 0</td>
<td>&#x2705;</td>
<td>&#x274C;</td>
<td>&#x274C;</td>
<td></td>
<td>[MLIR][ttnn.maxpool2d mlir pipeline] RuntimeError ttnn.max_pool2d currently only supports an input type of bfloat16 Failed to run MLIR compiler pass pipeline</td>
</tr>
<tr>
<td>Relu</td>
<td>Operand(type=Activation, shape=(1, 16, 28, 28), dtype=float32)</td>
<td></td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
<tr>
<td>Relu</td>
<td>Operand(type=Activation, shape=(1, 4, 14, 14), dtype=float32)</td>
<td></td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
<tr>
<td>Relu</td>
<td>Operand(type=Activation, shape=(1, 16, 14, 14), dtype=float32)</td>
<td></td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
<tr>
<td>Unsqueeze</td>
<td>Operand(type=Parameter, shape=(16,), dtype=float32)</td>
<td>dim : 1</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
<tr>
<td>Unsqueeze</td>
<td>Operand(type=Activation, shape=(16, 1), dtype=float32)</td>
<td>dim : 1</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
<tr>
<td>Unsqueeze</td>
<td>Operand(type=Parameter, shape=(4,), dtype=float32)</td>
<td>dim : 1</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
<tr>
<td>Unsqueeze</td>
<td>Operand(type=Activation, shape=(4, 1), dtype=float32)</td>
<td>dim : 1</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
<tr>
<td>Unsqueeze</td>
<td>Operand(type=Parameter, shape=(1,), dtype=float32)</td>
<td>dim : 1</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
<tr>
<td>Unsqueeze</td>
<td>Operand(type=Activation, shape=(1, 1), dtype=float32)</td>
<td>dim : 1</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td>&#x2705;</td>
<td></td>
<td></td>
</tr>
</tbody>
</table>
Loading
Loading