50 lines
1.3 KiB
YAML
50 lines
1.3 KiB
YAML
|
test_name: "test GLM-4.5 multi-dp"
|
||
|
|
model: "ZhipuAI/GLM-4.5"
|
||
|
|
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
|
||
|
|
|
||
|
|
deployment:
|
||
|
|
-
|
||
|
|
server_cmd: >
|
||
|
|
vllm serve "ZhipuAI/GLM-4.5"
|
||
|
|
--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 16
|
||
|
|
--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 "ZhipuAI/GLM-4.5"
|
||
|
|
--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 16
|
||
|
|
--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:
|