Skip to content
This repository has been archived by the owner on Aug 30, 2024. It is now read-only.

Commit

Permalink
Update supported_models.md (#150)
Browse files Browse the repository at this point in the history 
* Update supported_models.md
  • Loading branch information
@a32543254
a32543254 authored Mar 4, 2024
1 parent 7c2199f commit 603a661
Showing 1 changed file with 59 additions and 5 deletions.
64 changes: 59 additions & 5 deletions docs/supported_models.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -7,17 +7,19 @@ Neural Speed supports the following models:
<thead>
<tr>
<th rowspan="2">Model Name</th>
<th colspan="3">INT8</th>
<th colspan="3">INT4</th>
<th colspan="4">INT8</th>
<th colspan="4">INT4</th>
<th rowspan="2">Transformer Version</th>
</tr>
<tr>
<th>RTN</th>
<th>GPTQ</th>
<th>AWQ</th>
<th>AutoRound</th>
<th>RTN</th>
<th>GPTQ</th>
<th>AWQ</th>
<th>AutoRound</th>
</tr>
</thead>
<tbody>
Expand All @@ -31,6 +33,8 @@ Neural Speed supports the following models:
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>Latest</td>
</tr>
<tr>
Expand All @@ -42,6 +46,8 @@ Neural Speed supports the following models:
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>Latest</td>
</tr>
<td><a href="https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf" target="_blank" rel="noopener noreferrer">CodeLlama-7b</a></td>
Expand All @@ -51,6 +57,8 @@ Neural Speed supports the following models:
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>Latest</td>
</tr>
</tr>
Expand All @@ -61,36 +69,44 @@ Neural Speed supports the following models:
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>Latest</td>
</tr>
<tr>
<td><a href="https://huggingface.co/EleutherAI/gpt-j-6b" target="_blank" rel="noopener noreferrer">GPT-J-6B</a></td>
<td>✅</td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>Latest</td>
</tr>
<tr>
<td><a href="https://huggingface.co/EleutherAI/gpt-neox-20b" target="_blank" rel="noopener noreferrer">GPT-NeoX-20B</a></td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>Latest</td>
</tr>
<tr>
<td><a href="https://huggingface.co/databricks/dolly-v2-3b" target="_blank" rel="noopener noreferrer">Dolly-v2-3B</a></td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>4.28.1 or newer</td>
</tr>
<tr>
Expand All @@ -99,9 +115,11 @@ Neural Speed supports the following models:
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>Latest</td>
</tr>
<tr>
Expand All @@ -110,19 +128,23 @@ Neural Speed supports the following models:
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>Latest</td>
</tr>
<tr>
<td><a href="https://huggingface.co/bigscience/bloomz-7b1" target="_blank" rel="noopener noreferrer">BLOOM-7B</a></td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>Latest</td>
</tr>
<tr>
Expand All @@ -132,9 +154,11 @@ Neural Speed supports the following models:
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>Latest</td>
</tr>
<tr>
Expand All @@ -146,6 +170,8 @@ Neural Speed supports the following models:
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>Latest</td>
</tr>
<tr>
Expand All @@ -154,9 +180,11 @@ Neural Speed supports the following models:
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>4.33.1</td>
</tr>
<tr>
Expand All @@ -165,9 +193,11 @@ Neural Speed supports the following models:
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>4.33.1</td>
</tr>
<tr>
Expand All @@ -176,9 +206,11 @@ Neural Speed supports the following models:
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>4.36.0 or newer</td>
</tr>
<tr>
Expand All @@ -187,9 +219,11 @@ Neural Speed supports the following models:
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>Latest</td>
</tr>
<tr>
Expand All @@ -199,9 +233,11 @@ Neural Speed supports the following models:
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>Latest</td>
</tr>
<tr>
Expand All @@ -213,9 +249,11 @@ Neural Speed supports the following models:
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>Latest</td>
</tr>
</tbody>
Expand All @@ -227,15 +265,19 @@ Neural Speed supports the following models:
<thead>
<tr>
<th rowspan="2">Model Name</th>
<th colspan="2">INT8</th>
<th colspan="2">INT4</th>
<th colspan="4">INT8</th>
<th colspan="4">INT4</th>
<th rowspan="2">Transformer Version</th>
</tr>
<tr>
<th>RTN</th>
<th>GPTQ</th>
<th>AWQ</th>
<th>AutoRound</th>
<th>RTN</th>
<th>GPTQ</th>
<th>AWQ</th>
<th>AutoRound</th>
</tr>
</thead>
<tbody>
Expand All @@ -246,6 +288,10 @@ Neural Speed supports the following models:
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>Latest</td>
</tr>
<tr>
Expand All @@ -254,6 +300,10 @@ Neural Speed supports the following models:
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>✅</td>
<td>Latest</td>
</tr>
<tr>
Expand All @@ -262,8 +312,12 @@ Neural Speed supports the following models:
<a href="https://huggingface.co/bigcode/starcoder" target="_blank" rel="noopener noreferrer">StarCoder-15.5B</a></td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>✅</td>
<td> </td>
<td> </td>
<td> </td>
<td>Latest</td>
</tr>
</tbody>
Expand Down

0 comments on commit 603a661

Please sign in to comment.