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

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(