xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 00:45:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Docs] Correct multiprocessing design doc (#18964)

Browse Source 
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
This commit is contained in:
Lukas Geiger 2025-05-31 02:30:15 +01:00 committed by GitHub
parent 1dab4d5718
commit 0f71e24034
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docs/design/multiprocessing.md
View File

@ -22,13 +22,13 @@ This document describes how vLLM deals with these challenges.
[Python multiprocessing methods](https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods) include: [Python multiprocessing methods](https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods) include:
- `spawn` - spawn a new Python process. This will be the default as of Python - `spawn` - spawn a new Python process. The default on Windows and macOS.
3.14. In macOS, this is already the default.
- `fork` - Use `os.fork()` to fork the Python interpreter. This is the default - `fork` - Use `os.fork()` to fork the Python interpreter. The default on
in Python versions prior to 3.14. Linux for Python versions prior to 3.14.
- `forkserver` - Spawn a server process that will fork a new process on request. - `forkserver` - Spawn a server process that will fork a new process on request.
The default on Linux for Python version 3.14 and newer.
### Tradeoffs ### Tradeoffs