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>
52 lines
1.4 KiB
Python
52 lines
1.4 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
import pytest
|
|
|
|
from vllm.assets.audio import AudioAsset
|
|
|
|
|
|
def add_attention_backend(server_args, attention_config):
|
|
"""Append attention backend CLI arg if specified.
|
|
|
|
Args:
|
|
server_args: List of server arguments to extend in-place.
|
|
attention_config: Dict with 'backend' key, or None.
|
|
"""
|
|
if attention_config and "backend" in attention_config:
|
|
server_args.extend(["--attention-backend", attention_config["backend"]])
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def rocm_aiter_fa_attention():
|
|
"""Return attention config for transcription/translation tests on ROCm.
|
|
|
|
On ROCm, audio tests require ROCM_AITER_FA attention backend.
|
|
"""
|
|
from vllm.platforms import current_platform
|
|
|
|
if current_platform.is_rocm():
|
|
return {"backend": "ROCM_AITER_FA"}
|
|
return None
|
|
|
|
|
|
@pytest.fixture
|
|
def mary_had_lamb():
|
|
path = AudioAsset("mary_had_lamb").get_local_path()
|
|
with open(str(path), "rb") as f:
|
|
yield f
|
|
|
|
|
|
@pytest.fixture
|
|
def winning_call():
|
|
path = AudioAsset("winning_call").get_local_path()
|
|
with open(str(path), "rb") as f:
|
|
yield f
|
|
|
|
|
|
@pytest.fixture
|
|
def foscolo():
|
|
# Test translation it->en
|
|
path = AudioAsset("azacinto_foscolo").get_local_path()
|
|
with open(str(path), "rb") as f:
|
|
yield f
|