A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 23:30 UTC
[Doc] Improve OpenVINO installation doc (#13102)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Feb 11, 2025 at 18:02 UTC
deb6c1c6b4469984eb2a032099081f7f9e4ec8a8
1 file changed
+5
-3
docs/source/getting_started/installation/ai_accelerator/openvino.inc.md
+5
-3
@@ -19,17 +19,19 @@ Currently, there are no pre-built OpenVINO wheels.
19
20
### Build wheel from source
21
22
-First, install Python. For example, on Ubuntu 22.04, you can run:
22
+First, install Python and ensure you lave the latest pip. For example, on Ubuntu 22.04, you can run:
23
24
```console
25
sudo apt-get update -y
26
sudo apt-get install python3
27
+pip install --upgrade pip
28
```
29
29
-Second, install prerequisites vLLM OpenVINO backend installation:
30
+Second, clone vLLM and install prerequisites for the vLLM OpenVINO backend installation:
31
32
```console
32
-pip install --upgrade pip
33
+git clone https://github.com/vllm-project/vllm.git
34
+cd vllm
35
pip install -r requirements-build.txt --extra-index-url https://download.pytorch.org/whl/cpu
36
```
37