295018ec0f
### What this PR does / why we need it?
Based on the RFC:https://github.com/vllm-project/vllm-ascend/issues/5604
This PR is a refactoring of vllm_ascend/distributed, moving all
kv_transfer realtaed codes into a dedicated folder, which has already
been done in vLLM
### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef
---------
Signed-off-by: lty <linhebiwen@gmail.com>
107 lines
2.9 KiB
YAML
107 lines
2.9 KiB
YAML
test_name: "test Qwen3-VL-235B-A22B disaggregated_prefill"
|
|
model: "Qwen/Qwen3-VL-235B-A22B-Instruct"
|
|
num_nodes: 2
|
|
npu_per_node: 16
|
|
env_common:
|
|
VLLM_USE_MODELSCOPE: true
|
|
HCCL_BUFFSIZE: 1024
|
|
SERVER_PORT: 8080
|
|
OMP_PROC_BIND: false
|
|
OMP_NUM_THREADS: 1
|
|
HCCL_OP_EXPANSION_MODE: "AIV"
|
|
TASK_QUEUE_ENABLE: 1
|
|
PYTORCH_NPU_ALLOC_CONF: expandable_segments:True
|
|
|
|
disaggregated_prefill:
|
|
enabled: true
|
|
prefiller_host_index: [0]
|
|
decoder_host_index: [1]
|
|
|
|
deployment:
|
|
-
|
|
server_cmd: >
|
|
vllm serve "Qwen/Qwen3-VL-235B-A22B-Instruct"
|
|
--host 0.0.0.0
|
|
--port $SERVER_PORT
|
|
--data-parallel-size 2
|
|
--data-parallel-size-local 2
|
|
--tensor-parallel-size 8
|
|
--seed 1024
|
|
--enable-expert-parallel
|
|
--max-num-seqs 32
|
|
--max-model-len 8192
|
|
--max-num-batched-tokens 8192
|
|
--trust-remote-code
|
|
--no-enable-prefix-caching
|
|
--gpu-memory-utilization 0.9
|
|
--kv-transfer-config
|
|
'{"kv_connector": "MooncakeConnectorV1",
|
|
"kv_role": "kv_producer",
|
|
"kv_port": "30000",
|
|
"engine_id": "0",
|
|
"kv_connector_extra_config": {
|
|
"prefill": {
|
|
"dp_size": 2,
|
|
"tp_size": 8
|
|
},
|
|
"decode": {
|
|
"dp_size": 4,
|
|
"tp_size": 4
|
|
}
|
|
}
|
|
}'
|
|
-
|
|
server_cmd: >
|
|
vllm serve "Qwen/Qwen3-VL-235B-A22B-Instruct"
|
|
--host 0.0.0.0
|
|
--port $SERVER_PORT
|
|
--data-parallel-size 4
|
|
--data-parallel-size-local 4
|
|
--tensor-parallel-size 4
|
|
--seed 1024
|
|
--enable-expert-parallel
|
|
--max-num-seqs 32
|
|
--max-model-len 8192
|
|
--max-num-batched-tokens 8192
|
|
--trust-remote-code
|
|
--no-enable-prefix-caching
|
|
--gpu-memory-utilization 0.9
|
|
--compilation-config '{"cudagraph_mode":"FULL_DECODE_ONLY"}'
|
|
--kv-transfer-config
|
|
'{"kv_connector": "MooncakeConnectorV1",
|
|
"kv_role": "kv_consumer",
|
|
"kv_port": "30200",
|
|
"engine_id": "1",
|
|
"kv_connector_extra_config": {
|
|
"prefill": {
|
|
"dp_size": 2,
|
|
"tp_size": 8
|
|
},
|
|
"decode": {
|
|
"dp_size": 4,
|
|
"tp_size": 4
|
|
}
|
|
}
|
|
}'
|
|
benchmarks:
|
|
perf:
|
|
case_type: performance
|
|
dataset_path: vllm-ascend/textvqa-perf-1080p
|
|
request_conf: vllm_api_stream_chat
|
|
dataset_conf: textvqa/textvqa_gen_base64
|
|
num_prompts: 2800
|
|
max_out_len: 1500
|
|
batch_size: 64
|
|
request_rate: 11.2
|
|
baseline: 1
|
|
threshold: 0.97
|
|
acc:
|
|
case_type: accuracy
|
|
dataset_path: vllm-ascend/textvqa-lite
|
|
request_conf: vllm_api_stream_chat
|
|
dataset_conf: textvqa/textvqa_gen_base64
|
|
max_out_len: 7680
|
|
batch_size: 64
|
|
baseline: 85
|
|
threshold: 5
|