@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / f085995a7b
Fork 0

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 16, 09:30 UTC

[CI/Build] Remove unnecessary `fork_new_process` (#9484)

Cyrus Leung committed Oct 22, 2024 at 10:47 UTC f085995a7b073f0f4a330f469d9f489160e5b7a1
1 file changed +1 -1
tests/utils.py
+1 -1
@@ -587,7 +587,7 @@ def large_gpu_test(*, min_gb: int):
587 )
588
589 def wrapper(f: Callable[_P, None]) -> Callable[_P, None]:
590 - return test_skipif(fork_new_process_for_each_test(f))
590 + return test_skipif(f)
591
592 return wrapper
593