863a5a5a17
### What this PR does / why we need it?
As there is not accuracy test for qwen3-235B-A22B model
Test result:
dataset version metric mode vllm-api-general-chat
--------- --------- -------- ------ -----------------------
gsm8k 7cd45e accuracy gen 96.29
Times long for test case running: 30mintues
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
60 lines
1.6 KiB
YAML
60 lines
1.6 KiB
YAML
test_name: "test Qwen3-235B-A22B multi-dp"
|
|
model: "Qwen/Qwen3-235B-A22B"
|
|
num_nodes: 2
|
|
npu_per_node: 16
|
|
env_common:
|
|
VLLM_USE_MODELSCOPE: true
|
|
OMP_PROC_BIND: false
|
|
OMP_NUM_THREADS: 100
|
|
HCCL_BUFFSIZE: 1024
|
|
SERVER_PORT: 8080
|
|
NUMEXPR_MAX_THREADS: 128
|
|
|
|
deployment:
|
|
-
|
|
server_cmd: >
|
|
vllm serve "Qwen/Qwen3-235B-A22B"
|
|
--host 0.0.0.0
|
|
--port $SERVER_PORT
|
|
--data-parallel-size 4
|
|
--data-parallel-size-local 2
|
|
--data-parallel-address $LOCAL_IP
|
|
--data-parallel-rpc-port 13389
|
|
--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
|
|
-
|
|
server_cmd: >
|
|
vllm serve "Qwen/Qwen3-235B-A22B"
|
|
--headless
|
|
--data-parallel-size 4
|
|
--data-parallel-size-local 2
|
|
--data-parallel-start-rank 2
|
|
--data-parallel-address $MASTER_IP
|
|
--data-parallel-rpc-port 13389
|
|
--tensor-parallel-size 8
|
|
--seed 1024
|
|
--max-num-seqs 32
|
|
--max-model-len 8192
|
|
--max-num-batched-tokens 8192
|
|
--enable-expert-parallel
|
|
--trust-remote-code
|
|
--no-enable-prefix-caching
|
|
--gpu-memory-utilization 0.9
|
|
benchmarks:
|
|
acc:
|
|
case_type: accuracy
|
|
dataset_path: vllm-ascend/gsm8k
|
|
request_conf: vllm_api_general_chat
|
|
dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_chat_prompt
|
|
max_out_len: 7680
|
|
batch_size: 512
|
|
baseline: 95
|
|
threshold: 3
|