EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[P/D][main]Offline the llmdatadist connector related parts of the code and files. (#4780)

Browse Source 
### What this PR does / why we need it?
As support for the mooncake connector is now available, the llmdatadist
connector is no longer being maintained, so the llmdatadist-related
files need to be retired.

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
By ci

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
Signed-off-by: liziyu <liziyu16@huawei.com>
Co-authored-by: liziyu <liziyu16@huawei.com>
This commit is contained in:
wangxiaoteng888
2025-12-09 22:36:43 +08:00
committed by GitHub
parent 848419d1ba
commit a77045f355
19 changed files with 188 additions and 1819 deletions
Download Patch File Download Diff File Expand all files Collapse all files

72
tests/e2e/nightly/multi_node/config/models/DeepSeek-R1-W8A8-EPLB.yaml
View File

@@ -41,13 +41,21 @@ deployment:
--gpu-memory-utilization 0.9
--speculative-config '{"num_speculative_tokens": 1, "method":"mtp"}'
--kv-transfer-config
'{"kv_connector": "LLMDataDistCMgrConnector",
"kv_buffer_device": "npu",
'{"kv_connector": "MooncakeConnector",
"kv_role": "kv_producer",
"kv_parallel_size": 1,
"kv_port": "20001",
"kv_port": "30000",
"engine_id": "0",
"kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
"kv_connector_module_path": "vllm_ascend.distributed.mooncake_connector",
"kv_connector_extra_config": {
"prefill": {
"dp_size": 2,
"tp_size": 8
},
"decode": {
"dp_size": 32,
"tp_size": 1
}
}
}'
--additional-config
'{"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true,"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
@@ -71,13 +79,21 @@ deployment:
--gpu-memory-utilization 0.9
--speculative-config '{"num_speculative_tokens": 1, "method":"mtp"}'
--kv-transfer-config
'{"kv_connector": "LLMDataDistCMgrConnector",
"kv_buffer_device": "npu",
'{"kv_connector": "MooncakeConnector",
"kv_role": "kv_producer",
"kv_parallel_size": 1,
"kv_port": "20001",
"kv_port": "30100",
"engine_id": "1",
"kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
"kv_connector_module_path": "vllm_ascend.distributed.mooncake_connector",
"kv_connector_extra_config": {
"prefill": {
"dp_size": 2,
"tp_size": 8
},
"decode": {
"dp_size": 32,
"tp_size": 1
}
}
}'
--additional-config
'{"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true,"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
@@ -102,13 +118,21 @@ deployment:
--gpu-memory-utilization 0.9
--speculative-config '{"num_speculative_tokens": 1, "method":"mtp"}'
--kv-transfer-config
'{"kv_connector": "LLMDataDistCMgrConnector",
"kv_buffer_device": "npu",
'{"kv_connector": "MooncakeConnector",
"kv_role": "kv_consumer",
"kv_parallel_size": 1,
"kv_port": "20001",
"kv_port": "30200",
"engine_id": "2",
"kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
"kv_connector_module_path": "vllm_ascend.distributed.mooncake_connector",
"kv_connector_extra_config": {
"prefill": {
"dp_size": 2,
"tp_size": 8
},
"decode": {
"dp_size": 32,
"tp_size": 1
}
}
}'
--additional-config
'{"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true,"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'
@@ -132,13 +156,21 @@ deployment:
--gpu-memory-utilization 0.9
--speculative-config '{"num_speculative_tokens": 1, "method":"mtp"}'
--kv-transfer-config
'{"kv_connector": "LLMDataDistCMgrConnector",
"kv_buffer_device": "npu",
'{"kv_connector": "MooncakeConnector",
"kv_role": "kv_consumer",
"kv_parallel_size": 1,
"kv_port": "20001",
"kv_port": "30200",
"engine_id": "2",
"kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
"kv_connector_module_path": "vllm_ascend.distributed.mooncake_connector",
"kv_connector_extra_config": {
"prefill": {
"dp_size": 2,
"tp_size": 8
},
"decode": {
"dp_size": 32,
"tp_size": 1
}
}
}'
--additional-config
'{"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true,"dynamic_eplb":true,"num_iterations_eplb_update":2048,"num_wait_worker_iterations":200}'

78
tests/e2e/nightly/multi_node/config/models/DeepSeek-R1-W8A8.yaml
View File

@@ -40,13 +40,21 @@ deployment:
--gpu-memory-utilization 0.9
--speculative-config '{"num_speculative_tokens": 1, "method":"mtp"}'
--kv-transfer-config
'{"kv_connector": "LLMDataDistCMgrConnector",
"kv_buffer_device": "npu",
'{"kv_connector": "MooncakeConnector",
"kv_role": "kv_producer",
"kv_parallel_size": 1,
"kv_port": "20001",
"kv_port": "30000",
"engine_id": "0",
"kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
"kv_connector_module_path": "vllm_ascend.distributed.mooncake_connector",
"kv_connector_extra_config": {
"prefill": {
"dp_size": 2,
"tp_size": 8
},
"decode": {
"dp_size": 32,
"tp_size": 1
}
}
}'
--additional-config
'{"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true}'
@@ -70,13 +78,21 @@ deployment:
--gpu-memory-utilization 0.9
--speculative-config '{"num_speculative_tokens": 1, "method":"mtp"}'
--kv-transfer-config
'{"kv_connector": "LLMDataDistCMgrConnector",
"kv_buffer_device": "npu",
'{"kv_connector": "MooncakeConnector",
"kv_role": "kv_producer",
"kv_parallel_size": 1,
"kv_port": "20001",
"engine_id": "0",
"kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
"kv_port": "30100",
"engine_id": "1",
"kv_connector_module_path": "vllm_ascend.distributed.mooncake_connector",
"kv_connector_extra_config": {
"prefill": {
"dp_size": 2,
"tp_size": 8
},
"decode": {
"dp_size": 32,
"tp_size": 1
}
}
}'
--additional-config
'{"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true}'
@@ -101,13 +117,21 @@ deployment:
--gpu-memory-utilization 0.9
--speculative-config '{"num_speculative_tokens": 1, "method":"mtp"}'
--kv-transfer-config
'{"kv_connector": "LLMDataDistCMgrConnector",
"kv_buffer_device": "npu",
'{"kv_connector": "MooncakeConnector",
"kv_role": "kv_consumer",
"kv_parallel_size": 1,
"kv_port": "20001",
"engine_id": "0",
"kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
"kv_port": "30200",
"engine_id": "2",
"kv_connector_module_path": "vllm_ascend.distributed.mooncake_connector",
"kv_connector_extra_config": {
"prefill": {
"dp_size": 2,
"tp_size": 8
},
"decode": {
"dp_size": 32,
"tp_size": 1
}
}
}'
--additional-config
'{"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true}'
@@ -131,13 +155,21 @@ deployment:
--gpu-memory-utilization 0.9
--speculative-config '{"num_speculative_tokens": 1, "method":"mtp"}'
--kv-transfer-config
'{"kv_connector": "LLMDataDistCMgrConnector",
"kv_buffer_device": "npu",
'{"kv_connector": "MooncakeConnector",
"kv_role": "kv_consumer",
"kv_parallel_size": 1,
"kv_port": "20001",
"engine_id": "0",
"kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
"kv_port": "30200",
"engine_id": "2",
"kv_connector_module_path": "vllm_ascend.distributed.mooncake_connector",
"kv_connector_extra_config": {
"prefill": {
"dp_size": 2,
"tp_size": 8
},
"decode": {
"dp_size": 32,
"tp_size": 1
}
}
}'
--additional-config
'{"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true}'

3
tests/e2e/nightly/multi_node/config/multi_node_config.py
View File

@@ -127,9 +127,6 @@ class MultiNodeConfig:
master_ip = self.master_ip
if self.disaggregated_prefill:
self.envs[
"DISAGGREGATED_PREFILL_RANK_TABLE_PATH"] = self.disaggregated_prefill.get(
"ranktable_path")
if self.cur_index < self.decode_start_index:
# For prefiller nodes, use the default master ip(index==0) as DP master
master_ip = self.master_ip

25
tests/e2e/pd_disaggreate/run_edge_case_test.sh
View File

@@ -16,17 +16,6 @@ GIT_ROOT=$(git rev-parse --show-toplevel)
# Trap the SIGINT signal (triggered by Ctrl+C)
trap 'kill $(jobs -pr)' SIGINT SIGTERM EXIT
# Gen ranktable
RANKTABLE_PATH=${GIT_ROOT}/examples/disaggregate_prefill_v1/ranktable.json
if [ -f "$RANKTABLE_PATH" ]; then
rm "$RANKTABLE_PATH"
fi
cd ${GIT_ROOT}/examples/disaggregate_prefill_v1
LOCAL_HOST=`hostname -I|awk -F " " '{print$1}'`
bash gen_ranktable.sh --ips $LOCAL_HOST --network-card-name enp189s0f0 --prefill-device-cnt 1 --decode-device-cnt 1
cd -
export DISAGGREGATED_PREFILL_RANK_TABLE_PATH="$RANKTABLE_PATH"
# Waits for vLLM to start.
wait_for_server() {
local port=$1
@@ -69,12 +58,14 @@ run_tests_for_model() {
# Start prefill instance
PREFILL_PORT=8001
BASE_CMD="ASCEND_RT_VISIBLE_DEVICES=0 VLLM_ASCEND_LLMDD_RPC_PORT=5559 vllm serve $model_name \
BASE_CMD="ASCEND_RT_VISIBLE_DEVICES=0 vllm serve $model_name \
--port $PREFILL_PORT \
--seed 1024 \
--enforce-eager \
--disable-log-requests \
--gpu-memory-utilization 0.8 \
--kv-transfer-config '{\"kv_connector\":\"LLMDataDistCMgrConnector\",\"kv_role\":\"kv_producer\",\"kv_buffer_device\":\"npu\",\"kv_parallel_size\":\"1\",\"kv_port\":\"20001\",\"engine_id\":\"0\",\"kv_connector_module_path\":\"vllm_ascend.distributed.llmdatadist_c_mgr_connector\"}'"
--distributed-executor-backend mp \
--kv-transfer-config '{\"kv_connector\":\"MooncakeConnector\",\"kv_role\":\"kv_producer\",\"kv_port\":\"30000\",\"engine_id\":\"0\",\"kv_connector_module_path\":\"vllm_ascend.distributed.mooncake_connector\",\"kv_connector_extra_config\":{\"prefill\":{\"dp_size\":1,\"tp_size\":1},\"decode\":{\"dp_size\":1,\"tp_size\":1}}}'"
if [ -n "$model_args" ]; then
FULL_CMD="$BASE_CMD $model_args"
@@ -88,12 +79,14 @@ run_tests_for_model() {
DECODE_PORT=8002
# Build the command with or without model-specific args
BASE_CMD="ASCEND_RT_VISIBLE_DEVICES=1 VLLM_ASCEND_LLMDD_RPC_PORT=6000 vllm serve $model_name \
BASE_CMD="ASCEND_RT_VISIBLE_DEVICES=1 vllm serve $model_name \
--port $DECODE_PORT \
--seed 1024 \
--enforce-eager \
--disable-log-requests \
--gpu-memory-utilization 0.8 \
--kv-transfer-config '{\"kv_connector\":\"LLMDataDistCMgrConnector\",\"kv_role\":\"kv_consumer\",\"kv_buffer_device\":\"npu\",\"kv_parallel_size\":\"1\",\"kv_port\":\"20001\",\"engine_id\":\"0\",\"kv_connector_module_path\":\"vllm_ascend.distributed.llmdatadist_c_mgr_connector\"}'"
--distributed-executor-backend mp \
--kv-transfer-config '{\"kv_connector\":\"MooncakeConnector\",\"kv_role\":\"kv_consumer\",\"kv_port\":\"30100\",\"engine_id\":\"1\",\"kv_connector_module_path\":\"vllm_ascend.distributed.mooncake_connector\",\"kv_connector_extra_config\":{\"prefill\":{\"dp_size\":1,\"tp_size\":1},\"decode\":{\"dp_size\":1,\"tp_size\":1}}}'"
if [ -n "$model_args" ]; then
FULL_CMD="$BASE_CMD $model_args"
@@ -111,7 +104,7 @@ run_tests_for_model() {
# Build the command for the proxy server with all the hosts and ports
PROXY_PORT=8192
PROXY_CMD="python ${GIT_ROOT}/examples/disaggregate_prefill_v1/toy_proxy_server.py --port $PROXY_PORT"
PROXY_CMD="python ${GIT_ROOT}/examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py --port $PROXY_PORT"
PROXY_CMD+=" --prefiller-ports ${PREFILL_PORT}"
PROXY_CMD+=" --decoder-ports ${DECODE_PORT}"
# Start the proxy server

98
tests/ut/kv_connector/test_llmdatadist_connector.py
View File

@@ -1,98 +0,0 @@
# 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
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)
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
worker.pcp_rank = 0
worker.tp_size = worker_tp_rank + 1
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"

5
tests/ut/kv_connector/utils.py
View File

@@ -78,10 +78,9 @@ def create_vllm_config(
enable_prefix_caching=True,
)
kv_transfer_config = KVTransferConfig(
kv_connector="LLMDataDistCMgrConnector",
kv_connector="MooncakeConnector",
kv_role="kv_both",
kv_connector_module_path=
"vllm_ascend.distributed.llmdatadist_c_mgr_connector")
kv_connector_module_path="vllm_ascend.distributed.mooncake_connector")
return VllmConfig(scheduler_config=scheduler_config,
model_config=model_config,
cache_config=cache_config,