Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
20 lines
421 B
Python
20 lines
421 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
import pytest
|
|
|
|
from vllm.utils.torch_utils import (
|
|
create_kv_caches_with_random,
|
|
create_kv_caches_with_random_flash,
|
|
)
|
|
|
|
|
|
@pytest.fixture()
|
|
def kv_cache_factory():
|
|
return create_kv_caches_with_random
|
|
|
|
|
|
@pytest.fixture()
|
|
def kv_cache_factory_flashinfer():
|
|
return create_kv_caches_with_random_flash
|