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, 13:30 UTC
existing torch installation pip command fix for docs (#17059)
Atilla committed
Apr 24, 2025 at 20:07 UTC
49f189439d17f7f7614cc1db03f97089d5579d92
1 file changed
+1
-1
docs/source/getting_started/installation/gpu/cuda.inc.md
+1
-1
@@ -153,7 +153,7 @@ git clone https://github.com/vllm-project/vllm.git
153
cd vllm
154
python use_existing_torch.py
155
pip install -r requirements/build.txt
156
-pip install -e . --no-build-isolation
156
+pip install --no-build-isolation -e .
157
```
158
159
##### Use the local cutlass for compilation