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, 06:00 UTC
[doc] fix incorrect link (#19586)
Signed-off-by: reidliu41 <reid201711@gmail.com> Co-authored-by: reidliu41 <reid201711@gmail.com>
Reid committed
Jun 13, 2025 at 12:26 UTC
c707cfc12ea94f71f7aa044bfd5818d193344e74
1 file changed
+1
-1
docs/design/multiprocessing.md
+1
-1
@@ -123,7 +123,7 @@ what is happening. First, a log message from vLLM:
123
WARNING 12-11 14:50:37 multiproc_worker_utils.py:281] CUDA was previously
124
initialized. We must use the `spawn` multiprocessing start method. Setting
125
VLLM_WORKER_MULTIPROC_METHOD to 'spawn'. See
126
- https://docs.vllm.ai/en/latest/usage/debugging.html#python-multiprocessing
126
+ https://docs.vllm.ai/en/latest/usage/troubleshooting.html#python-multiprocessing
127
for more information.
128
```
129