xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-25 03:24:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI][ROCm][tests/v1/e2e] Fix multiprocessing launch for the test (#29123)

Browse Source 
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
This commit is contained in:
Divakar Verma 2025-12-02 14:46:10 -06:00 committed by GitHub
parent 1c593e117d
commit afb1e5b380
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 19 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
tests/v1/e2e/test_kv_sharing_fast_prefill.py
View File

@ -7,6 +7,7 @@ import pytest
from vllm import LLM, SamplingParams
from vllm.config import CompilationConfig, CompilationMode
from vllm.platforms import current_platform
from ...utils import check_answers, fork_new_process_for_each_test, prep_prompts
@ -43,15 +44,26 @@ def test_prompts():
return prompts
@fork_new_process_for_each_test
use_fork_for_test = (
fork_new_process_for_each_test if not current_platform.is_rocm() else lambda x: x
)
@use_fork_for_test
@pytest.mark.parametrize("kv_sharing_fast_prefill", [False, True])
@pytest.mark.parametrize("enforce_eager", [True, False])
def test_kv_sharing_fast_prefill(
monkeypatch: pytest.MonkeyPatch,
kv_sharing_fast_prefill: bool,
enforce_eager: bool,
test_prompts: list[str],
):
if not enforce_eager and current_platform.is_rocm():
# Relevant context: https://github.com/vllm-project/vllm/pull/29244
pytest.skip(
"ROCm: torch.compile produces incorrect output for gemma-3n's GELU "
"with tanh approximation. Use enforce_eager=True instead."
)
sampling_params = SamplingParams(temperature=0.0, max_tokens=100)
compilation_config = CompilationConfig(
# This allows vLLM compilation backend to handle allocating and
@ -65,7 +77,11 @@ def test_kv_sharing_fast_prefill(
with monkeypatch.context() as m:
# Make scheduling deterministic for reproducibility
m.setenv("VLLM_ENABLE_V1_MULTIPROCESSING", "0")
if current_platform.is_rocm():
# Use spawn to prevent cuda re-initialization error
m.setenv("VLLM_WORKER_MULTIPROC_METHOD", "spawn")
else:
m.setenv("VLLM_ENABLE_V1_MULTIPROCESSING", "0")
prompts, answer, indices = prep_prompts(batch_size)