biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Document multi-proc method selection for profiling (#23802)

Browse Source 
Signed-off-by: jdebache <jdebache@nvidia.com>
This commit is contained in:
Julien Debache
2025-09-01 15:28:26 +02:00
committed by GitHub
parent 7c8271cd1e
commit 41c80698b3
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/contributing/profiling.md
View File

@@ -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.