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 14, 05:30 UTC
[Doc]: Fix CPU install docs: force torch-backend=cpu to avoid GPU torchvision errors (#24033)
Signed-off-by: Kay Yan <kay.yan@daocloud.io>
Kay Yan committed
Sep 1, 2025 at 18:34 UTC
3e330fcb218e207bbc9eec3ed479a8b53b25c98d
1 file changed
+2
-2
docs/getting_started/installation/cpu/build.inc.md
+2
-2
@@ -16,8 +16,8 @@ cd vllm_source
16
Third, install required dependencies:
17
18
```bash
19
-uv pip install -r requirements/cpu-build.txt --torch-backend auto
20
-uv pip install -r requirements/cpu.txt --torch-backend auto
19
+uv pip install -r requirements/cpu-build.txt --torch-backend cpu
20
+uv pip install -r requirements/cpu.txt --torch-backend cpu
21
```
22
23
??? console "pip"