Skip to content

Commit 2630fd6

Browse files
authored
Update llama instructions for OpenVINO backend
1 parent 5875aa8 commit 2630fd6

File tree

1 file changed

+3
-1
lines changed

1 file changed

+3
-1
lines changed

examples/models/llama/README.md

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -94,6 +94,8 @@ Llama 3.2 1B and 3B performance was measured on Android OnePlus 12 device. The p
9494
</tr>
9595
</table>
9696

97+
[Please visit this section to try it on OpenVINO backend](../../openvino/llama/README.md).
98+
9799
## Llama 3/3.1 8B
98100
Since Llama 3 8B model needs at least 4-bit quantization to fit even within some of the highend phones, results presented here correspond to 4-bit groupwise post-training quantized (PTQ) model.
99101

@@ -136,7 +138,7 @@ Llama 3 8B performance was measured on the Samsung Galaxy S22, S24, and OnePlus
136138
</em>
137139
</p>
138140

139-
[Please visit this section to try it on non-CPU backend, including CoreML, MPS, Qualcomm HTP, MediaTek, or OpenVINO](non_cpu_backends.md).
141+
[Please visit this section to try it on non-CPU backend, including CoreML, MPS, Qualcomm HTP, or MediaTek](non_cpu_backends.md).
140142

141143
# Instructions
142144

0 commit comments

Comments
 (0)