From 41c80698b3849969dcb5c5e40d0991b0eb4821cc Mon Sep 17 00:00:00 2001 From: Julien Debache Date: Mon, 1 Sep 2025 15:28:26 +0200 Subject: [PATCH] Document multi-proc method selection for profiling (#23802) Signed-off-by: jdebache --- docs/contributing/profiling.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/contributing/profiling.md b/docs/contributing/profiling.md index 74627e906216..dffd62385e01 100644 --- a/docs/contributing/profiling.md +++ b/docs/contributing/profiling.md @@ -73,6 +73,8 @@ apt install nsight-systems-cli ### Example commands and usage +When profiling with `nsys`, it is advisable to set the environment variable `VLLM_WORKER_MULTIPROC_METHOD=spawn`. The default is to use the `fork` method instead of `spawn`. More information on the topic can be found in the [Nsight Systems release notes](https://docs.nvidia.com/nsight-systems/ReleaseNotes/index.html#general-issues). + #### Offline Inference For basic usage, you can just append `nsys profile -o report.nsys-rep --trace-fork-before-exec=true --cuda-graph-trace=node` before any existing script you would run for offline inference.