diff --git a/src/routes/blogs/olive-cli/+page.svx b/src/routes/blogs/olive-cli/+page.svx
index 8bf6c7ee1142a..b9102e0330033 100644
--- a/src/routes/blogs/olive-cli/+page.svx
+++ b/src/routes/blogs/olive-cli/+page.svx
@@ -37,7 +37,7 @@ At [Build 2023 Microsoft announced Olive (**O**NNX **Live**)](https://opensource
 <div class="m-auto w55">
 <img src="./olive-flow.png" alt="Olive workflow.">
 
-<i>High-Level Olive Workflow. These hardware targets can include various AI accelerators (NPU, GPU, CPU) provided by major hardware vendors such as Qualcomm, AMD, Nvidia, and Intel</i>
+<i>High-Level Olive Workflow. These hardware targets can include various AI accelerators (GPU, CPU) provided by major hardware vendors such as Qualcomm, AMD, Nvidia, and Intel</i>
 </div>
 <br/>
 
@@ -86,7 +86,6 @@ The command to run automatic optimizer for the Llama-3.2-1B-Instruct model on CP
 > **Tip:** If want to target:
 > - CUDA GPU, then update `--device` to `gpu` and `--provider` to `CUDAExecutionProvider`. 
 > - Windows DirectML, then update `--device` to `gpu` and `--provider` to `DmlExecutionProvider`.
-> - Qualcomm NPU, then update `--device` to `npu` and `--provider` to `QNNExecutionProvider`.
 >
 > Olive will apply the optimizations specific to the device and provider.