| 1 | { |
| 2 | "defaults": { |
| 3 | "qps_list": [ |
| 4 | "inf" |
| 5 | ], |
| 6 | "max_concurrency_list": [ |
| 7 | 12, |
| 8 | 16, |
| 9 | 24, |
| 10 | 32, |
| 11 | 64, |
| 12 | 128, |
| 13 | 200 |
| 14 | ], |
| 15 | "server_environment_variables": { |
| 16 | "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1, |
| 17 | "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120, |
| 18 | "VLLM_CPU_SGL_KERNEL": 1, |
| 19 | "VLLM_CPU_KVCACHE_SPACE": 40 |
| 20 | }, |
| 21 | "server_parameters": { |
| 22 | "model": "meta-llama/Llama-3.1-8B-Instruct", |
| 23 | "tensor_parallel_size": 1, |
| 24 | "dtype": "bfloat16", |
| 25 | "distributed_executor_backend": "mp", |
| 26 | "block_size": 128, |
| 27 | "trust_remote_code": "", |
| 28 | "disable_log_stats": "", |
| 29 | "enforce_eager": "", |
| 30 | "max_num_batched_tokens": 2048, |
| 31 | "max_num_seqs": 256, |
| 32 | "load_format": "dummy" |
| 33 | }, |
| 34 | "client_parameters": { |
| 35 | "model": "meta-llama/Llama-3.1-8B-Instruct", |
| 36 | "backend": "vllm", |
| 37 | "ignore-eos": "", |
| 38 | "temperature": 0, |
| 39 | "num_prompts": 200 |
| 40 | } |
| 41 | }, |
| 42 | "tests": [ |
| 43 | { |
| 44 | "test_name": "serving_llama8B_tp1_sharegpt", |
| 45 | "server_parameters": { |
| 46 | "tensor_parallel_size": 1 |
| 47 | }, |
| 48 | "client_parameters": { |
| 49 | "dataset_name": "sharegpt", |
| 50 | "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json" |
| 51 | } |
| 52 | }, |
| 53 | { |
| 54 | "test_name": "serving_llama8B_tp2_sharegpt", |
| 55 | "server_parameters": { |
| 56 | "tensor_parallel_size": 2 |
| 57 | }, |
| 58 | "client_parameters": { |
| 59 | "dataset_name": "sharegpt", |
| 60 | "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json" |
| 61 | } |
| 62 | }, |
| 63 | { |
| 64 | "test_name": "serving_llama8B_tp1_random_128_128", |
| 65 | "server_parameters": { |
| 66 | "tensor_parallel_size": 1 |
| 67 | }, |
| 68 | "client_parameters": { |
| 69 | "dataset_name": "random", |
| 70 | "random-input-len": 128, |
| 71 | "random-output-len": 128 |
| 72 | } |
| 73 | }, |
| 74 | { |
| 75 | "test_name": "serving_llama8B_tp2_random_128_128", |
| 76 | "server_parameters": { |
| 77 | "tensor_parallel_size": 2 |
| 78 | }, |
| 79 | "client_parameters": { |
| 80 | "dataset_name": "random", |
| 81 | "random-input-len": 128, |
| 82 | "random-output-len": 128 |
| 83 | } |
| 84 | }, |
| 85 | { |
| 86 | "test_name": "serving_llama8B_tp1_random_128_2048", |
| 87 | "server_parameters": { |
| 88 | "tensor_parallel_size": 1 |
| 89 | }, |
| 90 | "client_parameters": { |
| 91 | "dataset_name": "random", |
| 92 | "random-input-len": 128, |
| 93 | "random-output-len": 2048 |
| 94 | } |
| 95 | }, |
| 96 | { |
| 97 | "test_name": "serving_llama8B_tp2_random_128_2048", |
| 98 | "server_parameters": { |
| 99 | "tensor_parallel_size": 2 |
| 100 | }, |
| 101 | "client_parameters": { |
| 102 | "dataset_name": "random", |
| 103 | "random-input-len": 128, |
| 104 | "random-output-len": 2048 |
| 105 | } |
| 106 | }, |
| 107 | { |
| 108 | "test_name": "serving_llama8B_tp1_random_2048_128", |
| 109 | "server_parameters": { |
| 110 | "tensor_parallel_size": 1 |
| 111 | }, |
| 112 | "client_parameters": { |
| 113 | "dataset_name": "random", |
| 114 | "random-input-len": 2048, |
| 115 | "random-output-len": 128 |
| 116 | } |
| 117 | }, |
| 118 | { |
| 119 | "test_name": "serving_llama8B_tp2_random_2048_128", |
| 120 | "server_parameters": { |
| 121 | "tensor_parallel_size": 2 |
| 122 | }, |
| 123 | "client_parameters": { |
| 124 | "dataset_name": "random", |
| 125 | "random-input-len": 2048, |
| 126 | "random-output-len": 128 |
| 127 | } |
| 128 | } |
| 129 | ] |
| 130 | } |