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, 07:15 UTC
[Docs] Correct multiprocessing design doc (#18964)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Lukas Geiger committed
May 31, 2025 at 02:30 UTC
0f71e24034263363e48cdc6ae036e7ca057a4f44
1 file changed
+4
-4
docs/design/multiprocessing.md
+4
-4
@@ -22,13 +22,13 @@ This document describes how vLLM deals with these challenges.
22
23
[Python multiprocessing methods](https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods) include:
24
25
-- `spawn` - spawn a new Python process. This will be the default as of Python
26
- 3.14. In macOS, this is already the default.
25
+- `spawn` - spawn a new Python process. The default on Windows and macOS.
26
28
-- `fork` - Use `os.fork()` to fork the Python interpreter. This is the default
29
- in Python versions prior to 3.14.
27
+- `fork` - Use `os.fork()` to fork the Python interpreter. The default on
28
+ Linux for Python versions prior to 3.14.
29
30
- `forkserver` - Spawn a server process that will fork a new process on request.
31
+ The default on Linux for Python version 3.14 and newer.
32
33
### Tradeoffs
34