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>
19 lines
487 B
Python
19 lines
487 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
"""Pytest configuration for vLLM pooling tests."""
|
|
|
|
import pytest
|
|
|
|
from vllm.platforms import current_platform
|
|
|
|
|
|
@pytest.fixture
|
|
def siglip_attention_config():
|
|
"""Return attention config for SigLIP tests on ROCm.
|
|
|
|
On ROCm, SigLIP tests require FLEX_ATTENTION backend.
|
|
"""
|
|
if current_platform.is_rocm():
|
|
return {"backend": "FLEX_ATTENTION"}
|
|
return None
|