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, 19:30 UTC
[ci][test] finalize fork_new_process_for_each_test (#7114)
youkaichao committed
Aug 3, 2024 at 10:44 UTC
44dcb52e39ee6b2c9ef9e6497525e1e183c9d24b
1 file changed
+3
tests/utils.py
+3
@@ -360,6 +360,9 @@ def wait_for_gpu_memory_to_clear(devices: List[int],
360
361
362
def fork_new_process_for_each_test(f):
363
+ """Decorator to fork a new process for each test function.
364
+ See https://github.com/vllm-project/vllm/issues/7053 for more details.
365
+ """
366
367
@functools.wraps(f)
368
def wrapper(*args, **kwargs):