53 lines
1.4 KiB
YAML
53 lines
1.4 KiB
YAML
|
# ==========================================
|
||
|
|
# ACTUAL TEST CASES
|
||
|
|
# ==========================================
|
||
|
|
|
||
|
|
test_cases:
|
||
|
|
- name: "Kimi-K2-Thinking-TP16-Case"
|
||
|
|
model: "moonshotai/Kimi-K2-Thinking"
|
||
|
|
envs:
|
||
|
|
HCCL_BUFFSIZE: "1024"
|
||
|
|
TASK_QUEUE_ENABLE: "1"
|
||
|
|
OMP_PROC_BIND: "false"
|
||
|
|
HCCL_OP_EXPANSION_MODE: "AIV"
|
||
|
|
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
|
||
|
|
SERVER_PORT: "DEFAULT_PORT"
|
||
|
|
server_cmd:
|
||
|
|
- "--tensor-parallel-size"
|
||
|
|
- "16"
|
||
|
|
- "--port"
|
||
|
|
- "$SERVER_PORT"
|
||
|
|
- "--max-model-len"
|
||
|
|
- "8192"
|
||
|
|
- "--max-num-batched-tokens"
|
||
|
|
- "8192"
|
||
|
|
- "--max-num-seqs"
|
||
|
|
- "12"
|
||
|
|
- "--gpu-memory-utilization"
|
||
|
|
- "0.9"
|
||
|
|
- "--trust-remote-code"
|
||
|
|
- "--enable-expert-parallel"
|
||
|
|
- "--no-enable-prefix-caching"
|
||
|
|
benchmarks:
|
||
|
|
acc:
|
||
|
|
case_type: accuracy
|
||
|
|
dataset_path: vllm-ascend/gsm8k-lite
|
||
|
|
request_conf: vllm_api_general_chat
|
||
|
|
dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_chat_prompt
|
||
|
|
max_out_len: 4096
|
||
|
|
batch_size: 32
|
||
|
|
baseline: 95
|
||
|
|
threshold: 5
|
||
|
|
perf:
|
||
|
|
case_type: performance
|
||
|
|
dataset_path: vllm-ascend/GSM8K-in3500-bs400
|
||
|
|
request_conf: vllm_api_stream_chat
|
||
|
|
dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_str_perf
|
||
|
|
num_prompts: 512
|
||
|
|
max_out_len: 256
|
||
|
|
batch_size: 64
|
||
|
|
trust_remote_code: true
|
||
|
|
request_rate: 11.2
|
||
|
|
baseline: 1
|
||
|
|
threshold: 0.97
|