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 13, 04:30 UTC
[Doc] Fix macOS installation dependency resolution issue (#26721)
Signed-off-by: faisal shah <fashah@redhat.com>
Fasal Shah committed
Nov 14, 2025 at 18:13 UTC
8d3748d3c718dd1dfb1f7e9e0825bc9032bff75a
1 file changed
+6
-1
docs/getting_started/installation/cpu.apple.inc.md
+6
-1
@@ -28,10 +28,15 @@ After installation of XCode and the Command Line Tools, which include Apple Clan
28
```bash
29
git clone https://github.com/vllm-project/vllm.git
30
cd vllm
31
-uv pip install -r requirements/cpu.txt
31
+uv pip install -r requirements/cpu.txt --index-strategy unsafe-best-match
32
uv pip install -e .
33
```
34
35
+!!! tip
36
+ The `--index-strategy unsafe-best-match` flag is needed to resolve dependencies across multiple package indexes (PyTorch CPU index and PyPI). Without this flag, you may encounter `typing-extensions` version conflicts.
37
+
38
+ The term "unsafe" refers to the package resolution strategy, not security. By default, `uv` only searches the first index where a package is found to prevent dependency confusion attacks. This flag allows `uv` to search all configured indexes to find the best compatible versions. Since both PyTorch and PyPI are trusted package sources, using this strategy is safe and appropriate for vLLM installation.
39
+
40
!!! note
41
On macOS the `VLLM_TARGET_DEVICE` is automatically set to `cpu`, which is currently the only supported device.
42