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

[Bugfix][ROCm] running new process using spawn method for rocm in tests. (#14810)

Browse Source 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
vllmellm
2025-03-17 19:33:35 +08:00
committed by GitHub
parent 6eaf1e5c52
commit 2bb0e1a799
21 changed files with 174 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
tests/basic_correctness/test_cumem.py
View File

@@ -7,10 +7,10 @@ from vllm import LLM, SamplingParams
from vllm.device_allocator.cumem import CuMemAllocator
from vllm.utils import GiB_bytes
from ..utils import fork_new_process_for_each_test
from ..utils import create_new_process_for_each_test
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_python_error():
"""
Test if Python error occurs when there's low-level
@@ -36,7 +36,7 @@ def test_python_error():
allocator.wake_up()
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_basic_cumem():
# some tensors from default memory pool
shape = (1024, 1024)
@@ -69,7 +69,7 @@ def test_basic_cumem():
assert torch.allclose(output, torch.ones_like(output) * 3)
@fork_new_process_for_each_test
@create_new_process_for_each_test()
def test_cumem_with_cudagraph():
allocator = CuMemAllocator.get_instance()
with allocator.use_memory_pool():
@@ -114,7 +114,7 @@ def test_cumem_with_cudagraph():
assert torch.allclose(y, x + 1)
@fork_new_process_for_each_test
@create_new_process_for_each_test()
@pytest.mark.parametrize(
"model, use_v1",
[