00e3f9da46
Signed-off-by: Tsai, Louie <louie.tsai@intel.com> Signed-off-by: Louie Tsai <louie.tsai@intel.com> Co-authored-by: Li, Jiang <bigpyj64@gmail.com>
169 lines
5.5 KiB
JSON
169 lines
5.5 KiB
JSON
[
|
|
{
|
|
"test_name": "serving_llama8B_tp1_sharegpt",
|
|
"qps_list": [1, 4, 16, "inf"],
|
|
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
|
|
"server_environment_variables": {
|
|
"VLLM_RPC_TIMEOUT": 100000,
|
|
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
|
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
|
"VLLM_CPU_SGL_KERNEL": 1,
|
|
"VLLM_CPU_KVCACHE_SPACE": 40
|
|
},
|
|
"server_parameters": {
|
|
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
|
"tensor_parallel_size": 1,
|
|
"dtype": "bfloat16",
|
|
"distributed_executor_backend": "mp",
|
|
"block_size": 128,
|
|
"trust_remote_code": "",
|
|
"disable_log_stats": "",
|
|
"enforce_eager": "",
|
|
"max_num_batched_tokens": 2048,
|
|
"max_num_seqs": 256,
|
|
"load_format": "dummy"
|
|
},
|
|
"client_parameters": {
|
|
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
|
"backend": "vllm",
|
|
"dataset_name": "sharegpt",
|
|
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
|
"num_prompts": 200
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_llama8B_tp2_sharegpt",
|
|
"qps_list": [1, 4, 16, "inf"],
|
|
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
|
|
"server_environment_variables": {
|
|
"VLLM_RPC_TIMEOUT": 100000,
|
|
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
|
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
|
"VLLM_CPU_SGL_KERNEL": 1,
|
|
"VLLM_CPU_KVCACHE_SPACE": 40
|
|
},
|
|
"server_parameters": {
|
|
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
|
"tensor_parallel_size": 2,
|
|
"dtype": "bfloat16",
|
|
"distributed_executor_backend": "mp",
|
|
"block_size": 128,
|
|
"trust_remote_code": "",
|
|
"disable_log_stats": "",
|
|
"enforce_eager": "",
|
|
"max_num_batched_tokens": 2048,
|
|
"max_num_seqs": 256,
|
|
"load_format": "dummy"
|
|
},
|
|
"client_parameters": {
|
|
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
|
"backend": "vllm",
|
|
"dataset_name": "sharegpt",
|
|
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
|
"num_prompts": 200
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_llama8B_tp4_sharegpt",
|
|
"qps_list": [1, 4, 16, "inf"],
|
|
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
|
|
"server_environment_variables": {
|
|
"VLLM_RPC_TIMEOUT": 100000,
|
|
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
|
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
|
"VLLM_CPU_SGL_KERNEL": 1,
|
|
"VLLM_CPU_KVCACHE_SPACE": 40
|
|
},
|
|
"server_parameters": {
|
|
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
|
"tensor_parallel_size": 4,
|
|
"dtype": "bfloat16",
|
|
"distributed_executor_backend": "mp",
|
|
"block_size": 128,
|
|
"trust_remote_code": "",
|
|
"disable_log_stats": "",
|
|
"enforce_eager": "",
|
|
"max_num_batched_tokens": 2048,
|
|
"max_num_seqs": 256,
|
|
"load_format": "dummy"
|
|
},
|
|
"client_parameters": {
|
|
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
|
"backend": "vllm",
|
|
"dataset_name": "sharegpt",
|
|
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
|
"num_prompts": 200
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_llama8B_tp4_random_1024_128",
|
|
"qps_list": [1, 4, 16, "inf"],
|
|
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
|
|
"server_environment_variables": {
|
|
"VLLM_RPC_TIMEOUT": 100000,
|
|
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
|
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
|
"VLLM_CPU_SGL_KERNEL": 1,
|
|
"VLLM_CPU_KVCACHE_SPACE": 40
|
|
},
|
|
"server_parameters": {
|
|
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
|
"tensor_parallel_size": 4,
|
|
"dtype": "bfloat16",
|
|
"distributed_executor_backend": "mp",
|
|
"block_size": 128,
|
|
"trust_remote_code": "",
|
|
"enable_chunked_prefill": "",
|
|
"disable_log_stats": "",
|
|
"enforce_eager": "",
|
|
"max_num_batched_tokens": 2048,
|
|
"max_num_seqs": 256,
|
|
"load_format": "dummy"
|
|
},
|
|
"client_parameters": {
|
|
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
|
"backend": "vllm",
|
|
"dataset_name": "random",
|
|
"random-input-len": 1024,
|
|
"random-output-len": 128,
|
|
"ignore-eos": "",
|
|
"num_prompts": 100
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_llama8B_pp6_random_1024_128",
|
|
"qps_list": [1, 4, 16, "inf"],
|
|
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
|
|
"server_environment_variables": {
|
|
"VLLM_RPC_TIMEOUT": 100000,
|
|
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
|
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
|
"VLLM_CPU_SGL_KERNEL": 1,
|
|
"VLLM_CPU_KVCACHE_SPACE": 40
|
|
},
|
|
"server_parameters": {
|
|
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
|
"pipeline_parallel_size": 6,
|
|
"dtype": "bfloat16",
|
|
"distributed_executor_backend": "mp",
|
|
"block_size": 128,
|
|
"trust_remote_code": "",
|
|
"enable_chunked_prefill": "",
|
|
"disable_log_stats": "",
|
|
"enforce_eager": "",
|
|
"max_num_batched_tokens": 2048,
|
|
"max_num_seqs": 256,
|
|
"load_format": "dummy"
|
|
},
|
|
"client_parameters": {
|
|
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
|
"backend": "vllm",
|
|
"dataset_name": "random",
|
|
"random-input-len": 1024,
|
|
"random-output-len": 128,
|
|
"ignore-eos": "",
|
|
"num_prompts": 100
|
|
}
|
|
}
|
|
]
|