{
  "suite_id": "rs9_frontier_h20_tp1_profile_full32k_coder200_ts0667",
  "sim": "frontier_h20_tp1_profile_full32k",
  "frontier": {
    "root": "/tmp/replayserve-frontier-rs1b",
    "mode": "patched_scratch",
    "patches": [
      "patches/frontier-vllm-v1-prefix-cache-chunked-prefill.patch",
      "patches/frontier-vllm-0.11.1-profiling-compat.patch"
    ],
    "profile_source": "dash2:/home/admin/cpfs/wjh/replayserve_frontier_profiles/h20_tp1_qwen3_30ba3b_full32k_20260624"
  },
  "fixtures": [
    "coder_200_ts0667"
  ],
  "defaults": {
    "simulation_mode": "online",
    "sys_arch": "co-location",
    "cluster_scheduler": "sticky_round_robin",
    "replica_scheduler": "vllm_v1",
    "model_name": "qwen3-a3b-30b-moe",
    "device": "h20",
    "network_device": "h20_dgx",
    "attn_tensor_parallel_size": 1,
    "attn_data_parallel_size": 1,
    "moe_tensor_parallel_size": 1,
    "moe_expert_parallel_size": 1,
    "num_pipeline_stages": 1,
    "num_replicas": 1,
    "batch_size_cap": 64,
    "max_tokens_in_batch": 32768,
    "block_size": 16,
    "enable_prefix_caching": true,
    "enable_chunked_prefill": true,
    "long_prefill_token_threshold": 32768,
    "trace_max_tokens": 32768,
    "num_blocks_mode": "explicit",
    "num_blocks": 15281,
    "gpu_memory_utilization": 0.85,
    "non_kv_cache_overhead_bytes": 0,
    "decode_cuda_graph_mode": "none",
    "enable_dummy_mode": false,
    "linear_op_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/linear_op_full32k.csv",
    "atten_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/attention_combined.csv",
    "moe_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/moe_full32k.csv",
    "prediction_max_prefill_chunk_size": 18000,
    "prediction_max_batch_size": 128,
    "prediction_max_tokens_per_request": 32768,
    "skip_cpu_overhead_modeling": true,
    "no_cache": true,
    "dummy_execution_time_ms": 1.0
  },
  "configs": [
    {
      "id": "vllm_kv_15281_profile_full32k",
      "description": "H20 TP1 Qwen3-30B-A3B with explicit vLLM TP1 KV blocks and H20 CUDA_EVENT profile timing; 200-request replay with timestamps scaled by 2/3."
    }
  ]
}