A high-throughput and memory-efficient inference and serving engine for LLMs
[ROCm][Doc] Add installation notes about python version requirement (#45671)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
vllmellm committed
Jun 15, 2026 at 17:22 UTC
25c53d129302d354272e0a433fdac129be049e72
1 file changed
+13
docs/getting_started/installation/gpu.rocm.inc.md
+13
@@ -27,6 +27,19 @@ If you need a different ROCm version or want to use an existing PyTorch installa
27
--8<-- [end:set-up-using-python]
28
--8<-- [start:pre-built-wheels]
29
30
+!!! warning "Python 3.12 required for ROCm wheels"
31
+
32
+ ROCm pre-built wheels are only available for **Python 3.12**. If you are using a different Python version (e.g. 3.11 or 3.13), the installer **will silently fall back** to the CUDA wheel from PyPI, which will fail on AMD GPUs with errors like `libcudart.so: cannot open shared object file`.
33
+
34
+ To check your Python version: `python3 --version`
35
+
36
+ If you need Python 3.12, you can create an isolated environment with `uv`:
37
+
38
+ ```bash
39
+ uv venv --python 3.12 --seed --managed-python
40
+ source .venv/bin/activate
41
+ ```
42
+
43
To install the latest version of vLLM for Python 3.12, ROCm 7.0 and `glibc >= 2.35`.
44
45
```bash