8b79d4de52
### What this PR does / why we need it?
1.fix "TypeError: get_attn_backend() remove variable": [Refactor
`check_and_update_config`](https://github.com/vllm-project/vllm/pull/35122)
2.fix [Rename `compile_ranges_split_points` to
`compile_ranges_endpoints`](https://github.com/vllm-project/vllm/pull/36027)
3.fix "RuntimeError: device_allocator not a DeviceAllocator":[Replace
memory related torch.cuda
APIs"](https://github.com/vllm-project/vllm/pull/37031)
4.fix [Support multiple KV groups in OffloadingSpec
](https://github.com/vllm-project/vllm/pull/36610) removed
self.offloaded_block_size and changed self.gpu_block_size from a scalar
to a tuple of per-group block sizes, adding block_size_factor.
5.fix [Consolidate
SupportsEagle](https://github.com/vllm-project/vllm/pull/36063) renamed
get_eagle3_aux_hidden_state_layers() to
get_eagle3_default_aux_hidden_state_layers() and added a
supports_eagle3() guard before calling it.
### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?
E2E
- vLLM version: v0.17.0
- vLLM main:
8a680463fa
---------
Signed-off-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Claude Code <noreply@anthropic.com>
104 lines
3.3 KiB
Python
104 lines
3.3 KiB
Python
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# Copyright 2023 The vLLM team.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
# This file is a part of the vllm-ascend project.
|
|
#
|
|
|
|
import pytest
|
|
from vllm.utils.network_utils import get_open_port
|
|
|
|
from tests.e2e.conftest import DisaggEpdProxy, RemoteEPDServer
|
|
from tools.send_mm_request import send_image_request
|
|
|
|
MODELS = [
|
|
"Qwen/Qwen2.5-VL-7B-Instruct",
|
|
]
|
|
SHARED_STORAGE_PATH = "/dev/shm/epd/storage"
|
|
TENSOR_PARALLELS = [1]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize("model", MODELS)
|
|
@pytest.mark.parametrize("tp_size", TENSOR_PARALLELS)
|
|
async def test_models(model: str, tp_size: int) -> None:
|
|
from vllm_ascend.utils import vllm_version_is
|
|
|
|
if not vllm_version_is("0.17.0"):
|
|
pytest.skip(
|
|
"EPLB output is different without EPLB, see issue: https://github.com/vllm-project/vllm-ascend/issues/7408",
|
|
)
|
|
encode_port = get_open_port()
|
|
pd_port = get_open_port()
|
|
vllm_server_args = [
|
|
[
|
|
"--port",
|
|
str(encode_port),
|
|
"--model",
|
|
model,
|
|
"--gpu-memory-utilization",
|
|
"0.01",
|
|
"--tensor-parallel-size",
|
|
str(tp_size),
|
|
"--enforce-eager",
|
|
"--no-enable-prefix-caching",
|
|
"--max-model-len",
|
|
"10000",
|
|
"--max-num-batched-tokens",
|
|
"10000",
|
|
"--max-num-seqs",
|
|
"1",
|
|
"--ec-transfer-config",
|
|
'{"ec_connector_extra_config":{"shared_storage_path":"'
|
|
+ SHARED_STORAGE_PATH
|
|
+ '"},"ec_connector":"ECExampleConnector","ec_role": "ec_producer"}',
|
|
],
|
|
[
|
|
"--port",
|
|
str(pd_port),
|
|
"--model",
|
|
model,
|
|
"--gpu-memory-utilization",
|
|
"0.95",
|
|
"--tensor-parallel-size",
|
|
str(tp_size),
|
|
"--enforce-eager",
|
|
"--max-model-len",
|
|
"10000",
|
|
"--max-num-batched-tokens",
|
|
"10000",
|
|
"--max-num-seqs",
|
|
"128",
|
|
"--ec-transfer-config",
|
|
'{"ec_connector_extra_config":{"shared_storage_path":"'
|
|
+ SHARED_STORAGE_PATH
|
|
+ '"},"ec_connector":"ECExampleConnector","ec_role": "ec_consumer"}',
|
|
],
|
|
]
|
|
proxy_port = get_open_port()
|
|
proxy_args = [
|
|
"--host",
|
|
"127.0.0.1",
|
|
"--port",
|
|
str(proxy_port),
|
|
"--encode-servers-urls",
|
|
f"http://localhost:{encode_port}",
|
|
"--decode-servers-urls",
|
|
f"http://localhost:{pd_port}",
|
|
"--prefill-servers-urls",
|
|
"disable",
|
|
]
|
|
|
|
with RemoteEPDServer(vllm_serve_args=vllm_server_args) as _, DisaggEpdProxy(proxy_args=proxy_args) as proxy:
|
|
send_image_request(model, proxy)
|