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 3, 06:45 UTC
[CPU][DOC] Fix installation commands for Arm CPUs (#43115)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Fadi Arafeh committed
May 20, 2026 at 00:31 UTC
be16785998087f80ffac08b980603241e5da16ab
1 file changed
+5
-5
docs/getting_started/installation/cpu.arm.inc.md
+5
-5
@@ -20,12 +20,12 @@ Pre-built vLLM wheels for Arm are available since version 0.11.2. These wheels c
20
21
```bash
22
export VLLM_VERSION=$(curl -s https://api.github.com/repos/vllm-project/vllm/releases/latest | jq -r .tag_name | sed 's/^v//')
23
-uv pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cpu-cp38-abi3-manylinux_2_35_aarch64.whl
23
+uv pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cpu-cp38-abi3-manylinux_2_35_aarch64.whl --torch-backend cpu
24
```
25
26
??? console "pip"
27
```bash
28
- pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cpu-cp38-abi3-manylinux_2_35_aarch64.whl
28
+ pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cpu-cp38-abi3-manylinux_2_35_aarch64.whl --extra-index-url https://download.pytorch.org/whl/cpu
29
```
30
31
!!! warning "set `LD_PRELOAD`"
@@ -53,7 +53,7 @@ LLM inference is a fast-evolving field, and the latest code may contain bug fixe
53
To install from nightly index, run:
54
55
```bash
56
-uv pip install vllm --extra-index-url https://wheels.vllm.ai/nightly/cpu --index-strategy first-index
56
+uv pip install vllm --extra-index-url https://wheels.vllm.ai/nightly/cpu --index-strategy first-index --torch-backend cpu
57
```
58
59
??? console "pip (there's a caveat)"
@@ -63,7 +63,7 @@ uv pip install vllm --extra-index-url https://wheels.vllm.ai/nightly/cpu --index
63
If you insist on using `pip`, you have to specify the full URL (link address) of the wheel file (which can be obtained from https://wheels.vllm.ai/nightly/cpu/vllm).
64
65
```bash
66
- pip install https://wheels.vllm.ai/4fa7ce46f31cbd97b4651694caf9991cc395a259/vllm-0.13.0rc2.dev104%2Bg4fa7ce46f.cpu-cp38-abi3-manylinux_2_35_aarch64.whl # current nightly build (the filename will change!)
66
+ pip install https://wheels.vllm.ai/4fa7ce46f31cbd97b4651694caf9991cc395a259/vllm-0.13.0rc2.dev104%2Bg4fa7ce46f.cpu-cp38-abi3-manylinux_2_35_aarch64.whl --extra-index-url https://download.pytorch.org/whl/cpu # current nightly build (the filename will change!)
67
```
68
69
#### Install specific revisions
@@ -72,7 +72,7 @@ If you want to access the wheels for previous commits (e.g. to bisect the behavi
72
73
```bash
74
export VLLM_COMMIT=730bd35378bf2a5b56b6d3a45be28b3092d26519 # use full commit hash from the main branch
75
-uv pip install vllm --extra-index-url https://wheels.vllm.ai/${VLLM_COMMIT}/cpu --index-strategy first-index
75
+uv pip install vllm --extra-index-url https://wheels.vllm.ai/${VLLM_COMMIT}/cpu --index-strategy first-index --torch-backend cpu
76
```
77
78
--8<-- [end:pre-built-wheels]