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, 14:45 UTC
[Doc] Make sure to update vLLM when installing latest code (#16781)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Apr 17, 2025 at 20:53 UTC
dbe7f07001955d6ba745f297203fee0aa0fbc5cf
1 file changed
+4
-2
docs/source/getting_started/installation/gpu/cuda.inc.md
+4
-2
@@ -46,7 +46,7 @@ LLM inference is a fast-evolving field, and the latest code may contain bug fixe
46
##### Install the latest code using `pip`
47
48
```console
49
-pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
49
+pip install -U vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
50
```
51
52
`--pre` is required for `pip` to consider pre-released versions.
@@ -65,9 +65,11 @@ Note that the wheels are built with Python 3.8 ABI (see [PEP 425](https://peps.p
65
Another way to install the latest code is to use `uv`:
66
67
```console
68
-uv pip install vllm --extra-index-url https://wheels.vllm.ai/nightly
68
+uv pip install -U vllm --extra-index-url https://wheels.vllm.ai/nightly
69
```
70
71
+##### Install specific revisions using `uv`
72
+
73
If you want to access the wheels for previous commits (e.g. to bisect the behavior change, performance regression), you can specify the commit hash in the URL:
74
75
```console