[Doc] Fix manylinux tag in installation guide (#47913)
Signed-off-by: Nick Cao <ncao@redhat.com>
Nick Cao committed
Jul 7, 2026 at 16:34 UTC
47c40bfe8a7c3db338ef58c7f622d6bca33e38f9
4 files changed
+9
-9
docs/contributing/ci/nightly_builds.md
+1
-1
@@ -14,7 +14,7 @@ Wheels are built in the `Release` pipeline (`.buildkite/release-pipeline.yaml`)
14
Each build step:
15
16
1. Builds the wheel in a Docker container.
17
-2. Renames the wheel filename to use the correct manylinux tag (currently `manylinux_2_31`) for PEP 600 compliance.
17
+2. Renames the wheel filename to use the correct manylinux tag (currently `manylinux_2_28`) for PEP 600 compliance.
18
3. Uploads the wheel to S3 bucket `vllm-wheels` under `/{commit_hash}/`.
19
20
### Index Generation
docs/getting_started/installation/cpu.arm.inc.md
+3
-3
@@ -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-${VLLM_VERSION}+cpu-cp38-abi3-manylinux_2_35_aarch64.whl --torch-backend cpu
23
+uv pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cpu-cp38-abi3-manylinux_2_34_aarch64.whl --torch-backend cpu
24
```
25
26
??? console "pip"
27
```bash
28
- pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cpu-cp38-abi3-manylinux_2_35_aarch64.whl --extra-index-url https://download.pytorch.org/whl/cpu
28
+ pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cpu-cp38-abi3-manylinux_2_34_aarch64.whl --extra-index-url https://download.pytorch.org/whl/cpu
29
```
30
31
!!! warning "set `LD_PRELOAD`"
@@ -63,7 +63,7 @@ uv pip install vllm --extra-index-url https://wheels.vllm.ai/nightly/cpu --index
63
If you insist on using `pip`, you have to specify the full URL (link address) of the wheel file (which can be obtained from https://wheels.vllm.ai/nightly/cpu/vllm).
64
65
```bash
66
- pip install https://wheels.vllm.ai/4fa7ce46f31cbd97b4651694caf9991cc395a259/vllm-0.13.0rc2.dev104%2Bg4fa7ce46f.cpu-cp38-abi3-manylinux_2_35_aarch64.whl --extra-index-url https://download.pytorch.org/whl/cpu # current nightly build (the filename will change!)
66
+ pip install https://wheels.vllm.ai/2f3f441f84bd5b35ec8aa9fcfffb540f107da8a7/vllm-0.23.1rc1.dev901%2Bg2f3f441f8.cpu-cp38-abi3-manylinux_2_34_aarch64.whl --extra-index-url https://download.pytorch.org/whl/cpu # current nightly build (the filename will change!)
67
```
68
69
#### Install specific revisions
docs/getting_started/installation/cpu.x86.inc.md
+2
-2
@@ -24,13 +24,13 @@ Pre-built vLLM wheels for x86 with AVX512/AVX2 are available since version 0.17.
24
export VLLM_VERSION=$(curl -s https://api.github.com/repos/vllm-project/vllm/releases/latest | jq -r .tag_name | sed 's/^v//')
25
26
# use uv
27
-uv pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cpu-cp38-abi3-manylinux_2_35_x86_64.whl --torch-backend cpu
27
+uv pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cpu-cp38-abi3-manylinux_2_34_x86_64.whl --torch-backend cpu
28
```
29
30
??? console "pip"
31
```bash
32
# use pip
33
- pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cpu-cp38-abi3-manylinux_2_35_x86_64.whl --extra-index-url https://download.pytorch.org/whl/cpu
33
+ pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cpu-cp38-abi3-manylinux_2_34_x86_64.whl --extra-index-url https://download.pytorch.org/whl/cpu
34
```
35
!!! warning "set `LD_PRELOAD`"
36
Before use vLLM CPU installed via wheels, make sure TCMalloc and Intel OpenMP are installed and added to `LD_PRELOAD`:
docs/getting_started/installation/gpu.cuda.inc.md
+3
-3
@@ -43,7 +43,7 @@ As of now, vLLM's binaries are compiled with CUDA 12.9 and public PyTorch releas
43
export VLLM_VERSION=$(curl -s https://api.github.com/repos/vllm-project/vllm/releases/latest | jq -r .tag_name | sed 's/^v//')
44
export CUDA_VERSION=130 # or other
45
export CPU_ARCH=$(uname -m) # x86_64 or aarch64
46
-uv pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cu${CUDA_VERSION}-cp38-abi3-manylinux_2_35_${CPU_ARCH}.whl --extra-index-url https://download.pytorch.org/whl/cu${CUDA_VERSION}
46
+uv pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cu${CUDA_VERSION}-cp38-abi3-manylinux_2_28_${CPU_ARCH}.whl --extra-index-url https://download.pytorch.org/whl/cu${CUDA_VERSION}
47
```
48
49
#### Install the latest code
@@ -68,8 +68,8 @@ uv pip install -U vllm \
68
If you insist on using `pip`, you have to specify the full URL of the wheel file (which can be obtained from the web page).
69
70
```bash
71
- pip install -U https://wheels.vllm.ai/nightly/vllm-0.11.2.dev399%2Bg3c7461c18-cp38-abi3-manylinux_2_31_x86_64.whl # current nightly build (the filename will change!)
72
- pip install -U https://wheels.vllm.ai/${VLLM_COMMIT}/vllm-0.11.2.dev399%2Bg3c7461c18-cp38-abi3-manylinux_2_31_x86_64.whl # from specific commit
71
+ pip install -U https://wheels.vllm.ai/2f3f441f84bd5b35ec8aa9fcfffb540f107da8a7/vllm-0.23.1rc1.dev901%2Bg2f3f441f8-cp38-abi3-manylinux_2_28_x86_64.whl # current nightly build (the filename will change!)
72
+ pip install -U https://wheels.vllm.ai/${VLLM_COMMIT}/vllm-0.23.1rc1.dev901%2Bg2f3f441f8-cp38-abi3-manylinux_2_28_x86_64.whl # from specific commit
73
```
74
75
##### Install specific revisions