Files
xc-llm-ascend/tests/ut/kv_connector/test_llmdatadist_connector.py

97 lines
3.6 KiB
Python
Raw Normal View History

Disaggregate prefill for kv cache register style (#950) ### What this PR does / why we need it? This PR adopt `LLMDataDist` for kv cache register and `pull_blocks` style disaggregate prefill implementation. The interface implementation mainly follows the design of NIXL PR https://github.com/vllm-project/vllm/pull/17751/files#diff-7eaad0b7dee0626bf29d10081b0f0c5e3ea15a4af97e7b182a4e0d35f8346953 . This PR can be test with the following step: - Generate the rank table for all machine. - execute`toy_proxy.py` to launch the disaggregate prefill proxy server, specify the prefill ip, port and the decode ip, port - Run the prefill server and decode server. - send the request to the disaggregate prefill proxy ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.9.2 - vLLM main: https://github.com/vllm-project/vllm/commit/8d0a01a5f2b53794e4bc6b734d7b63cb8a9b7d7d --------- Signed-off-by: ganyi <pleaplusone.gy@gmail.com> Signed-off-by: machenglong <machenglong_yewu@cmss.chinamobile.com> Signed-off-by: liziyu179 <3475441767@qq.com> Signed-off-by: underfitc <hucong24@huawei.com> Signed-off-by: zouyida2052 <zouyida@huawei.com> Signed-off-by: liziyu <liziyu16@huawei.com> Signed-off-by: underfituu <hzhucong@163.com> Co-authored-by: machenglong <machenglong_yewu@cmss.chinamobile.com> Co-authored-by: liziyu179 <3475441767@qq.com> Co-authored-by: underfitc <hucong24@huawei.com> Co-authored-by: zouyida2052 <zouyida@huawei.com> Co-authored-by: liziyu <liziyu16@huawei.com> Co-authored-by: underfituu <hzhucong@163.com>
2025-07-26 17:15:47 +08:00
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
import os
import types
Disaggregate prefill for kv cache register style (#950) ### What this PR does / why we need it? This PR adopt `LLMDataDist` for kv cache register and `pull_blocks` style disaggregate prefill implementation. The interface implementation mainly follows the design of NIXL PR https://github.com/vllm-project/vllm/pull/17751/files#diff-7eaad0b7dee0626bf29d10081b0f0c5e3ea15a4af97e7b182a4e0d35f8346953 . This PR can be test with the following step: - Generate the rank table for all machine. - execute`toy_proxy.py` to launch the disaggregate prefill proxy server, specify the prefill ip, port and the decode ip, port - Run the prefill server and decode server. - send the request to the disaggregate prefill proxy ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.9.2 - vLLM main: https://github.com/vllm-project/vllm/commit/8d0a01a5f2b53794e4bc6b734d7b63cb8a9b7d7d --------- Signed-off-by: ganyi <pleaplusone.gy@gmail.com> Signed-off-by: machenglong <machenglong_yewu@cmss.chinamobile.com> Signed-off-by: liziyu179 <3475441767@qq.com> Signed-off-by: underfitc <hucong24@huawei.com> Signed-off-by: zouyida2052 <zouyida@huawei.com> Signed-off-by: liziyu <liziyu16@huawei.com> Signed-off-by: underfituu <hzhucong@163.com> Co-authored-by: machenglong <machenglong_yewu@cmss.chinamobile.com> Co-authored-by: liziyu179 <3475441767@qq.com> Co-authored-by: underfitc <hucong24@huawei.com> Co-authored-by: zouyida2052 <zouyida@huawei.com> Co-authored-by: liziyu <liziyu16@huawei.com> Co-authored-by: underfituu <hzhucong@163.com>
2025-07-26 17:15:47 +08:00
from tests.ut.kv_connector.utils import (create_request, create_scheduler,
create_vllm_config)
from vllm_ascend.distributed.llmdatadist_c_mgr_connector import (
LLMDataDistCMgrConnectorMetadata, LLMDataDistCMgrConnectorWorker, LLMRole)
Disaggregate prefill for kv cache register style (#950) ### What this PR does / why we need it? This PR adopt `LLMDataDist` for kv cache register and `pull_blocks` style disaggregate prefill implementation. The interface implementation mainly follows the design of NIXL PR https://github.com/vllm-project/vllm/pull/17751/files#diff-7eaad0b7dee0626bf29d10081b0f0c5e3ea15a4af97e7b182a4e0d35f8346953 . This PR can be test with the following step: - Generate the rank table for all machine. - execute`toy_proxy.py` to launch the disaggregate prefill proxy server, specify the prefill ip, port and the decode ip, port - Run the prefill server and decode server. - send the request to the disaggregate prefill proxy ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.9.2 - vLLM main: https://github.com/vllm-project/vllm/commit/8d0a01a5f2b53794e4bc6b734d7b63cb8a9b7d7d --------- Signed-off-by: ganyi <pleaplusone.gy@gmail.com> Signed-off-by: machenglong <machenglong_yewu@cmss.chinamobile.com> Signed-off-by: liziyu179 <3475441767@qq.com> Signed-off-by: underfitc <hucong24@huawei.com> Signed-off-by: zouyida2052 <zouyida@huawei.com> Signed-off-by: liziyu <liziyu16@huawei.com> Signed-off-by: underfituu <hzhucong@163.com> Co-authored-by: machenglong <machenglong_yewu@cmss.chinamobile.com> Co-authored-by: liziyu179 <3475441767@qq.com> Co-authored-by: underfitc <hucong24@huawei.com> Co-authored-by: zouyida2052 <zouyida@huawei.com> Co-authored-by: liziyu <liziyu16@huawei.com> Co-authored-by: underfituu <hzhucong@163.com>
2025-07-26 17:15:47 +08:00
def test_basic_inferface():
"""Unit test for basic LLMDataDistCMgrConnector interface functionality."""
vllm_config = create_vllm_config()
scheduler = create_scheduler(vllm_config)
# 2 Full Blocks and 1 Half Block.
BLOCK_SIZE = vllm_config.cache_config.block_size
NUM_EXTERNAL_FULL_BLOCKS = 2
NUM_TOKENS = int(BLOCK_SIZE * (NUM_EXTERNAL_FULL_BLOCKS + 0.5))
request = create_request(request_id=1,
num_tokens=NUM_TOKENS,
do_remote_prefill=True)
request_id = request.request_id
scheduler.add_request(request)
# Remote Prefill, triggers LLMDataDistCMgrConnectorMetadata.
scheduler_output = scheduler.schedule()
kv_connector_metadata = scheduler_output.kv_connector_metadata
assert kv_connector_metadata is not None
assert isinstance(kv_connector_metadata, LLMDataDistCMgrConnectorMetadata)
assert len(kv_connector_metadata.requests) == 1
assert request_id in kv_connector_metadata.requests
req_meta = kv_connector_metadata.requests[request_id]
for block_id, block in zip(
req_meta.local_block_ids, scheduler.kv_cache_manager.coordinator.
single_type_managers[0].req_to_blocks[request_id]):
assert block_id == block.block_id
def test_read_agent_metadata():
rank_table = {
"version":
"1.2",
"server_count":
"2",
"prefill_device_list": [{
"server_id": "192.168.1.1",
"device_id": "0",
"device_ip": "10.30.0.1",
"cluster_id": "0",
}, {
"server_id": "192.168.1.1",
"device_id": "1",
"device_ip": "10.30.0.2",
"cluster_id": "1",
}, {
"server_id": "192.168.1.2",
"device_id": "0",
"device_ip": "10.30.0.3",
"cluster_id": "2",
}, {
"server_id": "192.168.1.2",
"device_id": "1",
"device_ip": "10.30.0.4",
"cluster_id": "3",
}]
}
def get_device_ip(worker_local_ip, worker_tp_rank, worker_visible_devices):
old_visible_devices = os.environ.get("ASCEND_RT_VISIBLE_DEVICES", "")
worker = types.SimpleNamespace()
worker.local_ip = worker_local_ip
worker.tp_rank = worker_tp_rank
worker.llm_datadist_role = LLMRole.PROMPT
os.environ["ASCEND_RT_VISIBLE_DEVICES"] = worker_visible_devices
agent_metadata = LLMDataDistCMgrConnectorWorker.read_agent_metadata(
worker, rank_table)
os.environ["ASCEND_RT_VISIBLE_DEVICES"] = old_visible_devices
return agent_metadata.device_ip
assert get_device_ip("192.168.1.1", 0, "0") == "10.30.0.1"
assert get_device_ip("192.168.1.1", 0, "1") == "10.30.0.2"
assert get_device_ip("192.168.1.2", 0, "0") == "10.30.0.3"
assert get_device_ip("192.168.1.2", 0, "1") == "10.30.0.4"
assert get_device_ip("192.168.1.1", 0, "0,1") == "10.30.0.1"
assert get_device_ip("192.168.1.1", 1, "0,1") == "10.30.0.2"
assert get_device_ip("192.168.1.1", 0, "") == "10.30.0.1"
assert get_device_ip("192.168.1.1", 1, "") == "10.30.0.2"