We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 23f6617 commit ab79f50Copy full SHA for ab79f50
1 file changed
docs/linux.rst
@@ -2,13 +2,17 @@
2
Linux Installation Instructions
3
#########################
4
5
-Ryzen AI for Linux supports compiling and running AI models on the AMD Neural Processing Unit (NPU). The current release supports:
6
7
-- CNN models in INT8 format
8
-- CNN models in BF16 format
9
-- NLP models (e.g., BERT, encoder-based) in BF16 format
+Ryzen AI for Linux supports running AI models on the AMD Neural Processing Unit (NPU) with the current release supported for STX, KRK platforms.
+
+With this release, users can now compile and run AI models using the following formats:
10
+- CNN models in INT8
11
+- CNN models in BF16
12
+- NLP models (e.g., BERT, encoder-based) in BF16
13
- LLMs (NPU-only flow)
-- Platforms - STX, KRK
14
15
16
17
18
*************
0 commit comments