{
  "profile": "mi50-fp16-tp2-mtp0",
  "image": "sha256:b6fa047585772ad215c9dd1cf6ff0a57dc37039743aab0637ace0753c20ff2e4",
  "container": "99381d2f6797e72404e8e186fec8c4bd3744a515945517d05b5b8548a689c542",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 25.37,
  "retest_logged_model_load_seconds": 16.160363,
  "retest_logged_available_KV_GiB": null,
  "retest_explicit_KV_budget_bytes": 4495769600,
  "retest_KV_budget_GiB": 4.18701171875,
  "retest_KV_budget_scope": "Explicit byte budget; profiling skipped",
  "retest_logged_GPU_KV_tokens": 33712,
  "retest_logged_context_capacity_x": 1.02,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/mi50-fp16-tp2-mtp0/service-final.log",
  "source_log_sha256": "9baac6ec7141f36335e506c7777e974cae19185b140c8112860fc3fbb3c05edb",
  "sealed_index_sha256": "e4f8ebde61b26ca3d5a8e83d60d7ec38e19c442b556cfe06683fa5c49a7ecff3",
  "source_lines": {
    "model_load": {
      "line": 122,
      "text": "(Worker pid=196) (Worker_TP0 pid=196) INFO 10-26 21:50:52 [gpu_model_runner.py:4584] Model loading took 25.37 GiB memory and 16.160363 seconds"
    },
    "explicit_KV_budget": {
      "line": 7,
      "text": "(APIServer pid=1) INFO 10-26 21:49:16 [utils.py:228] non-default args: {'model_tag': '/opt/local-models/Qwen3.8-27B', 'enable_auto_tool_choice': True, 'tool_call_parser': 'qwen3_coder', 'host': '0.0.0.0', 'port': 8001, 'model': '/opt/local-models/Qwen3.8-27B', 'trust_remote_code': True, 'dtype': 'half', 'max_model_len': 131072, 'served_model_name': ['Qwen/Qwen3.8-27B'], 'hf_overrides': {'architectures': ['Qwen3_5ForCausalLM']}, 'generation_config': 'vllm', 'reasoning_parser': 'qwen3', 'tensor_parallel_size': 2, 'worker_cls': 'vllm.fp16_matrix_worker.Worker', 'gpu_memory_utilization': 0.95, 'kv_cache_memory_bytes': 4495769600, 'enable_prefix_caching': False, 'mamba_ssm_cache_dtype': 'float32', 'language_model_only': True, 'max_num_batched_tokens': 4, 'max_num_seqs': 2, 'async_scheduling': True, 'optimization_level': '3'}"
    },
    "explicit_budget_worker_reports": [
      {
        "line": 134,
        "text": "(Worker pid=196) (Worker_TP0 pid=196) INFO 10-26 21:51:57 [gpu_worker.py:380] Initial free memory 31.71 GiB, reserved 4.19 GiB memory for KV Cache as specified by kv_cache_memory_bytes config and skipped memory profiling. This does not respect the gpu_memory_utilization config. Only use kv_cache_memory_bytes config when you want manual control of KV cache memory size. If OOM'ed, check the difference of initial free memory between the current run and the previous run where kv_cache_memory_bytes is suggested and update it correspondingly."
      },
      {
        "line": 135,
        "text": "(Worker pid=197) (Worker_TP1 pid=197) INFO 10-26 21:51:57 [gpu_worker.py:380] Initial free memory 31.71 GiB, reserved 4.19 GiB memory for KV Cache as specified by kv_cache_memory_bytes config and skipped memory profiling. This does not respect the gpu_memory_utilization config. Only use kv_cache_memory_bytes config when you want manual control of KV cache memory size. If OOM'ed, check the difference of initial free memory between the current run and the previous run where kv_cache_memory_bytes is suggested and update it correspondingly."
      }
    ],
    "grouped_KV_tokens": {
      "line": 136,
      "text": "(EngineCore_DP0 pid=178) INFO 10-26 21:51:57 [kv_cache_utils.py:1314] GPU KV cache size: 33,712 tokens"
    },
    "context_capacity": {
      "line": 137,
      "text": "(EngineCore_DP0 pid=178) INFO 10-26 21:51:57 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 1.02x"
    }
  },
  "limits": "Model-load delta and automatic available-KV values are rounded engine reports, not measured physical VRAM or exact tensor-byte totals. Explicit budgets are configuration values confirmed in the loaded engine, not profiled availability. Grouped KV tokens and concurrency use the engine hybrid-cache accounting; they are not proof of a completed full-context request or an exact request ceiling."
}
