| 1 | [ |
| 2 | { |
| 3 | "test_name": "llama8B_tp1_genai_perf", |
| 4 | "qps_list": [4,8,16,32], |
| 5 | "common_parameters": { |
| 6 | "model": "meta-llama/Meta-Llama-3-8B-Instruct", |
| 7 | "tp": 1, |
| 8 | "port": 8000, |
| 9 | "num_prompts": 500, |
| 10 | "reuse_server": false |
| 11 | }, |
| 12 | "vllm_server_parameters": { |
| 13 | "disable_log_stats": "", |
| 14 | "gpu_memory_utilization": 0.9, |
| 15 | "max_num_seqs": 512, |
| 16 | "dtype": "bfloat16" |
| 17 | }, |
| 18 | "genai_perf_input_parameters": { |
| 19 | } |
| 20 | } |
| 21 | ] |