73 lines
1.6 KiB
YAML
73 lines
1.6 KiB
YAML
|
# ==========================================
|
||
|
|
# Shared Configurations
|
||
|
|
# ==========================================
|
||
|
|
|
||
|
|
_envs: &envs
|
||
|
|
HCCL_BUFFSIZE: "1024"
|
||
|
|
SERVER_PORT: "DEFAULT_PORT"
|
||
|
|
|
||
|
|
_server_cmd: &server_cmd
|
||
|
|
- "--no-enable-prefix-caching"
|
||
|
|
- "--enable-expert-parallel"
|
||
|
|
- "--tensor-parallel-size"
|
||
|
|
- "8"
|
||
|
|
- "--data-parallel-size"
|
||
|
|
- "2"
|
||
|
|
- "--port"
|
||
|
|
- "$SERVER_PORT"
|
||
|
|
- "--max-model-len"
|
||
|
|
- "8192"
|
||
|
|
- "--max-num-batched-tokens"
|
||
|
|
- "8192"
|
||
|
|
- "--block-size"
|
||
|
|
- "16"
|
||
|
|
- "--trust-remote-code"
|
||
|
|
- "--gpu-memory-utilization"
|
||
|
|
- "0.9"
|
||
|
|
|
||
|
|
_benchmarks: &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: 8
|
||
|
|
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: 16
|
||
|
|
max_out_len: 1500
|
||
|
|
batch_size: 8
|
||
|
|
request_rate: 0
|
||
|
|
baseline: 1
|
||
|
|
threshold: 0.97
|
||
|
|
|
||
|
|
# ==========================================
|
||
|
|
# ACTUAL TEST CASES
|
||
|
|
# ==========================================
|
||
|
|
|
||
|
|
test_cases:
|
||
|
|
- name: "GLM-4.5-TP8-DP2-fullgraph"
|
||
|
|
model: "ZhipuAI/GLM-4.5"
|
||
|
|
envs:
|
||
|
|
<<: *envs
|
||
|
|
server_cmd: *server_cmd
|
||
|
|
server_cmd_extra:
|
||
|
|
- "--compilation-config"
|
||
|
|
- '{"cudagraph_capture": [1,2,4,8,16], "cudagraph_model":"FULL_DECODE_ONLY"}'
|
||
|
|
benchmarks:
|
||
|
|
<<: *benchmarks
|
||
|
|
|
||
|
|
- name: "GLM-4.5-TP8-DP2-eager"
|
||
|
|
model: "ZhipuAI/GLM-4.5"
|
||
|
|
envs:
|
||
|
|
<<: *envs
|
||
|
|
server_cmd: *server_cmd
|
||
|
|
benchmarks:
|
||
|
|
<<: *benchmarks
|