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>
13 lines
491 B
Python
13 lines
491 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
import pytest
|
|
|
|
import vllm.model_executor.layers.batch_invariant as batch_invariant
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def enable_batch_invariant_mode(monkeypatch: pytest.MonkeyPatch):
|
|
"""Automatically enable batch invariant kernel overrides for all tests."""
|
|
monkeypatch.setattr(batch_invariant, "VLLM_BATCH_INVARIANT", True)
|
|
monkeypatch.setenv("VLLM_BATCH_INVARIANT", "1")
|