Skip to content

Commit 344c9e4

Browse files
authored
Arm backend: Fix documentation after adding tutorial. (pytorch#22964)
Updated documentation with docgen.py cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell @rascani --------- Signed-off-by: Elena Zhelezina <elena.zhelezina@arm.com>
1 parent 3887eea commit 344c9e4

4 files changed

Lines changed: 7 additions & 4 deletions

File tree

‎backends/arm/scripts/docgen/vgf/backends-arm-vgf-overview.md.in‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -87,6 +87,7 @@ described in the rest of this guide but with a concrete end-to-end sample.
8787

8888
**→{doc}`/backends/arm-vgf/VGF_op_support` — VGF supported operators.**
8989

90+
**→{doc}`/backends/arm-vgf/tutorials/vgf-dynamic-w8a8-quantization` — Dynamic W8A8 quantization tutorial.**
9091

9192
```{toctree}
9293
:maxdepth: 2
@@ -98,4 +99,5 @@ arm-vgf-quantization
9899
arm-vgf-troubleshooting
99100
tutorials/vgf-getting-started
100101
VGF_op_support
102+
tutorials/vgf-dynamic-w8a8-quantization
101103
```

‎backends/arm/scripts/docgen/vgf/backends-arm-vgf-quantization.md.in‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -13,6 +13,8 @@ The quantization schemes supported by the VGF Backend are:
1313

1414
Weight-only quantization is not currently supported on the VGF backend.
1515

16+
For an end-to-end example of configuring and exporting dynamic W8A8 Linear layers, see the {doc}`Dynamic W8A8 Quantization Tutorial </backends/arm-vgf/tutorials/vgf-dynamic-w8a8-quantization>`.
17+
1618
### Partial Quantization
1719

1820
The VGF backend supports partial quantization, where only parts of the model

‎docs/source/backends/arm-vgf/arm-vgf-overview.md‎

Lines changed: 2 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -140,10 +140,9 @@ described in the rest of this guide but with a concrete end-to-end sample.
140140

141141
**→{doc}`/backends/arm-vgf/tutorials/vgf-getting-started` — Getting started tutorial.**
142142

143-
**→{doc}`/backends/arm-vgf/tutorials/vgf-dynamic-w8a8-quantization` — Dynamic W8A8 quantization tutorial.**
144-
145143
**→{doc}`/backends/arm-vgf/VGF_op_support` — VGF supported operators.**
146144

145+
**→{doc}`/backends/arm-vgf/tutorials/vgf-dynamic-w8a8-quantization` — Dynamic W8A8 quantization tutorial.**
147146

148147
```{toctree}
149148
:maxdepth: 2
@@ -154,6 +153,6 @@ arm-vgf-partitioner
154153
arm-vgf-quantization
155154
arm-vgf-troubleshooting
156155
tutorials/vgf-getting-started
157-
tutorials/vgf-dynamic-w8a8-quantization
158156
VGF_op_support
157+
tutorials/vgf-dynamic-w8a8-quantization
159158
```

‎docs/source/backends/arm-vgf/arm-vgf-quantization.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -13,7 +13,7 @@ The quantization schemes supported by the VGF Backend are:
1313

1414
Weight-only quantization is not currently supported on the VGF backend.
1515

16-
For an end-to-end example of configuring and exporting dynamic W8A8 Linear layers, see the [Dynamic W8A8 Quantization Tutorial](tutorials/vgf-dynamic-w8a8-quantization.md).
16+
For an end-to-end example of configuring and exporting dynamic W8A8 Linear layers, see the {doc}`Dynamic W8A8 Quantization Tutorial </backends/arm-vgf/tutorials/vgf-dynamic-w8a8-quantization>`.
1717

1818
### Partial Quantization
1919

0 commit comments

Comments
 (0)