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, 08:30 UTC
[Doc] fix list formatting (#18624)
Signed-off-by: David Xia <david@davidxia.com>
David Xia committed
May 23, 2025 at 12:41 UTC
8ddd1cf26ae484481126f6f9af198879b2da8a41
1 file changed
+4
-3
docs/getting_started/installation/gpu/cuda.inc.md
+4
-3
@@ -102,10 +102,11 @@ VLLM_USE_PRECOMPILED=1 pip install --editable .
102
```
103
104
This command will do the following:
105
+
106
1. Look for the current branch in your vLLM clone.
106
-2. Identify the corresponding base commit in the main branch.
107
-3. Download the pre-built wheel of the base commit.
108
-4. Use its compiled libraries in the installation.
107
+1. Identify the corresponding base commit in the main branch.
108
+1. Download the pre-built wheel of the base commit.
109
+1. Use its compiled libraries in the installation.
110
111
!!! note
112
1. If you change C++ or kernel code, you cannot use Python-only build; otherwise you will see an import error about library not found or undefined symbol.