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

[CI] Move applicable tests to CPU (#24080)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Reza Barazesh
2025-09-30 09:45:20 -04:00
committed by GitHub
parent 80608ba5af
commit bc546f76a1
39 changed files with 136 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/v1/core/test_async_scheduler.py
View File

@@ -11,6 +11,8 @@ from vllm.v1.utils import ConstantList
from .utils import create_requests, create_scheduler
pytestmark = pytest.mark.cpu_test
def _make_model_runner_output(
scheduler_output: SchedulerOutput, ) -> ModelRunnerOutput:

3
tests/v1/core/test_encoder_cache_manager.py
View File

@@ -1,9 +1,12 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import pytest
from vllm.multimodal.inputs import MultiModalFeatureSpec, PlaceholderRange
from vllm.v1.core.encoder_cache_manager import EncoderCacheManager
pytestmark = pytest.mark.cpu_test
# ------------------ Mock Classes ------------------ #
class MockRequest:

2
tests/v1/core/test_kv_cache_utils.py
View File

@@ -32,6 +32,8 @@ from vllm.v1.request import Request
# yapf: enable
pytestmark = pytest.mark.cpu_test
@pytest.fixture(autouse=True)
def _auto_init_hash_fn(request):

4
tests/v1/core/test_prefix_caching.py
View File

@@ -25,6 +25,8 @@ from vllm.v1.core.kv_cache_utils import (BlockHash, BlockHashWithGroupId,
from vllm.v1.kv_cache_interface import (FullAttentionSpec, KVCacheConfig,
KVCacheGroupSpec, SlidingWindowSpec)
pytestmark = pytest.mark.cpu_test
@pytest.fixture(autouse=True)
def _auto_init_hash_fn(request):
@@ -1267,7 +1269,7 @@ def test_kv_cache_events(blocks_to_cache: int):
def test_eagle_enabled_removes_last_block():
"""Verify Eagle does NOT remove blocks when request
"""Verify Eagle does NOT remove blocks when request
length is divisible by block size."""
block_size = 16
manager = KVCacheManager(

2
tests/v1/core/test_scheduler.py
View File

@@ -23,6 +23,8 @@ from vllm.v1.structured_output.request import StructuredOutputRequest
from .utils import EOS_TOKEN_ID, create_requests, create_scheduler
pytestmark = pytest.mark.cpu_test
def test_add_requests():
scheduler = create_scheduler()

3
tests/v1/core/test_single_type_kv_cache_manager.py
View File

@@ -3,6 +3,7 @@
import random
import pytest
import torch
from vllm.v1.core.block_pool import BlockPool
@@ -13,6 +14,8 @@ from vllm.v1.core.single_type_kv_cache_manager import (
from vllm.v1.kv_cache_interface import (ChunkedLocalAttentionSpec,
SlidingWindowSpec)
pytestmark = pytest.mark.cpu_test
def get_sliding_window_manager(sliding_window_spec, block_pool):
return SlidingWindowManager(sliding_window_spec,