{ "model": "Qwen2.5-3B", "accelerator": "L4", "scheduler": "continuous_fcfs", "quantization": "int8", "arrival_process": "poisson", "request_rate_rps": 4.0, "duration_s": 30, "prompt_tokens_mean": 512, "prompt_tokens_cv": 0.5, "output_tokens_mean": 64, "output_tokens_cv": 0.6, "max_batch_size": 16, "max_batch_tokens": 8192, "slo_ttft_ms": 500, "slo_e2e_ms": 5000, "slo_attainment_target": 0.99, "seed": 7 }