{
  "rows": [
    {
      "row": 27,
      "original_host": "10.0.0.20",
      "logged_model_load_delta_GiB": 6.75,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 109.895363,
      "logged_available_KV_GiB": 22.79,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 373360,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 11.32,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "1983ec5523a46271ddc4be71898407fe3211b4ad867af0641f94f757d35f9721",
      "source_archive": "historical-recovered/host10.0.0.20-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/gguf-vllm-test/vnext-contract-runs/20260629T003817Z-gguf-dense27b-tp8",
      "source_lines": {
        "load": {
          "number": 4589,
          "text": "(Worker pid=227) (Worker_TP0 pid=227) INFO 06-29 00:43:29 [gpu_model_runner.py:4579] Model loading took 6.75 GiB memory and 109.895363 seconds"
        },
        "KV": {
          "number": 5172,
          "text": "(Worker pid=227) (Worker_TP0 pid=227) INFO 06-29 00:46:17 [gpu_worker.py:453] Available KV cache memory: 22.79 GiB"
        },
        "tokens": {
          "number": 5175,
          "text": "(EngineCore_DP0 pid=200) INFO 06-29 00:46:17 [kv_cache_utils.py:1314] GPU KV cache size: 373,360 tokens"
        },
        "capacity": {
          "number": 5176,
          "text": "(EngineCore_DP0 pid=200) INFO 06-29 00:46:17 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.32x"
        },
        "engine": {
          "number": 64,
          "text": "(EngineCore_DP0 pid=200) INFO 06-29 00:41:15 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-27b-f16-gguf/Qwen3.6-27B-F16.gguf', speculative_config=None, tokenizer='Qwen/Qwen3.6-27B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=gguf, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=gguf, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen3.6-27B-F16-GGUF-lmheadunquant, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': PosixPath('/runwork/debug_dump'), 'cache_dir': '/runwork/compile_cache', 'compile_cache_save_format': 'unpacked', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [4], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': True, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 4, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 28,
      "original_host": "10.0.0.30",
      "logged_model_load_delta_GiB": 6.75,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 121.718155,
      "logged_available_KV_GiB": 22.79,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 373360,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 11.32,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "c954e80c7e73a96ae72d149bfefde298e35ede878ea1d50e3d8a8b4051bd22aa",
      "source_archive": "historical-recovered/host10.0.0.30-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/gguf-vllm-test/vnext-contract-runs/20260629T003817Z-gguf-dense27b-tp8",
      "source_lines": {
        "load": {
          "number": 4589,
          "text": "(Worker pid=227) (Worker_TP0 pid=227) INFO 06-29 00:43:42 [gpu_model_runner.py:4579] Model loading took 6.75 GiB memory and 121.718155 seconds"
        },
        "KV": {
          "number": 5172,
          "text": "(Worker pid=227) (Worker_TP0 pid=227) INFO 06-29 00:46:32 [gpu_worker.py:453] Available KV cache memory: 22.79 GiB"
        },
        "tokens": {
          "number": 5175,
          "text": "(EngineCore_DP0 pid=200) INFO 06-29 00:46:32 [kv_cache_utils.py:1314] GPU KV cache size: 373,360 tokens"
        },
        "capacity": {
          "number": 5176,
          "text": "(EngineCore_DP0 pid=200) INFO 06-29 00:46:32 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.32x"
        },
        "engine": {
          "number": 64,
          "text": "(EngineCore_DP0 pid=200) INFO 06-29 00:41:16 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-27b-f16-gguf/Qwen3.6-27B-F16.gguf', speculative_config=None, tokenizer='Qwen/Qwen3.6-27B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=gguf, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=gguf, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen3.6-27B-F16-GGUF-lmheadunquant, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': PosixPath('/runwork/debug_dump'), 'cache_dir': '/runwork/compile_cache', 'compile_cache_save_format': 'unpacked', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [4], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': True, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 4, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 29,
      "original_host": "10.0.0.20",
      "logged_model_load_delta_GiB": 6.84,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 7.221931,
      "logged_available_KV_GiB": 22.64,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 370864,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 11.25,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "7b29916dd30992ee4d28b5e1b69537e1adfb8405d4bb0bc254c1314d926e1efb",
      "source_archive": "historical-recovered/host10.0.0.20-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/gguf-vllm-test/vnext-package-runs/hf_dense27b_dot20_releasebundle_freshcache_20260628T203743Z/launch",
      "source_lines": {
        "load": {
          "number": 723,
          "text": "(Worker pid=327) (Worker_TP0 pid=327) INFO 06-28 20:39:17 [gpu_model_runner.py:4579] Model loading took 6.84 GiB memory and 7.221931 seconds"
        },
        "KV": {
          "number": 1273,
          "text": "(Worker pid=327) (Worker_TP0 pid=327) INFO 06-28 20:40:54 [gpu_worker.py:453] Available KV cache memory: 22.64 GiB"
        },
        "tokens": {
          "number": 1284,
          "text": "(EngineCore_DP0 pid=273) INFO 06-28 20:40:55 [kv_cache_utils.py:1314] GPU KV cache size: 370,864 tokens"
        },
        "capacity": {
          "number": 1285,
          "text": "(EngineCore_DP0 pid=273) INFO 06-28 20:40:55 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.25x"
        },
        "engine": {
          "number": 57,
          "text": "(EngineCore_DP0 pid=273) INFO 06-28 20:38:44 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/models--Qwen--Qwen3.6-27B/snapshots/6a9e13bd6fc8f0983b9b99948120bc37f49c13e9', speculative_config=None, tokenizer='/opt/local-models/models--Qwen--Qwen3.6-27B/snapshots/6a9e13bd6fc8f0983b9b99948120bc37f49c13e9', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen3.6-27B-HF-CausalLM, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [4], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 4, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 30,
      "original_host": "10.0.0.20",
      "logged_model_load_delta_GiB": 8.88,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 189.378052,
      "logged_available_KV_GiB": 19.91,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 521696,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 15.82,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "b89b1bada4eac6d54c85c9f77c9c1aa0aee0fb9ade0f826fbeb8e919bf371f4c",
      "source_archive": "historical-recovered/host10.0.0.20-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/gguf-vllm-test/vnext-contract-runs/20260629T003817Z-hf-moe35b-tp8",
      "source_lines": {
        "load": {
          "number": 193,
          "text": "(Worker pid=189) (Worker_TP0 pid=189) INFO 06-29 01:42:17 [gpu_model_runner.py:4579] Model loading took 8.88 GiB memory and 189.378052 seconds"
        },
        "KV": {
          "number": 308,
          "text": "(Worker pid=189) (Worker_TP0 pid=189) INFO 06-29 01:43:40 [gpu_worker.py:453] Available KV cache memory: 19.91 GiB"
        },
        "tokens": {
          "number": 315,
          "text": "(EngineCore_DP0 pid=171) INFO 06-29 01:43:41 [kv_cache_utils.py:1314] GPU KV cache size: 521,696 tokens"
        },
        "capacity": {
          "number": 316,
          "text": "(EngineCore_DP0 pid=171) INFO 06-29 01:43:41 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 15.82x"
        },
        "engine": {
          "number": 33,
          "text": "(EngineCore_DP0 pid=171) INFO 06-29 01:38:37 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/root/.cache/huggingface/hub/models--Qwen--Qwen3.6-35B-A3B/snapshots/995ad96eacd98c81ed38be0c5b274b04031597b0', speculative_config=None, tokenizer='/root/.cache/huggingface/hub/models--Qwen--Qwen3.6-35B-A3B/snapshots/995ad96eacd98c81ed38be0c5b274b04031597b0', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen/Qwen3.6-35B-A3B, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 512, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 31,
      "original_host": "10.0.0.30",
      "logged_model_load_delta_GiB": 8.88,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 191.364916,
      "logged_available_KV_GiB": 19.91,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 521696,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 15.82,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "72649d16114bbe7ecda6325c3b0eff1b7e054304b6dcfb050476b2307b2ee7ba",
      "source_archive": "historical-recovered/host10.0.0.30-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/gguf-vllm-test/vnext-contract-runs/20260629T003817Z-hf-moe35b-tp8",
      "source_lines": {
        "load": {
          "number": 193,
          "text": "(Worker pid=189) (Worker_TP0 pid=189) INFO 06-29 01:42:22 [gpu_model_runner.py:4579] Model loading took 8.88 GiB memory and 191.364916 seconds"
        },
        "KV": {
          "number": 308,
          "text": "(Worker pid=189) (Worker_TP0 pid=189) INFO 06-29 01:43:44 [gpu_worker.py:453] Available KV cache memory: 19.91 GiB"
        },
        "tokens": {
          "number": 315,
          "text": "(EngineCore_DP0 pid=171) INFO 06-29 01:43:45 [kv_cache_utils.py:1314] GPU KV cache size: 521,696 tokens"
        },
        "capacity": {
          "number": 316,
          "text": "(EngineCore_DP0 pid=171) INFO 06-29 01:43:45 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 15.82x"
        },
        "engine": {
          "number": 33,
          "text": "(EngineCore_DP0 pid=171) INFO 06-29 01:38:36 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/root/.cache/huggingface/hub/models--Qwen--Qwen3.6-35B-A3B/snapshots/995ad96eacd98c81ed38be0c5b274b04031597b0', speculative_config=None, tokenizer='/root/.cache/huggingface/hub/models--Qwen--Qwen3.6-35B-A3B/snapshots/995ad96eacd98c81ed38be0c5b274b04031597b0', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen/Qwen3.6-35B-A3B, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 512, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 32,
      "original_host": "10.0.0.30",
      "logged_model_load_delta_GiB": 6.75,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 109.957728,
      "logged_available_KV_GiB": 23.15,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 379184,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 11.5,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "759f71b82d879600a80aa25cd5340f4bcf248dd73784a58ffaa097e640117f39",
      "source_archive": "historical-recovered/host10.0.0.30-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/vnext-release-repro/localaiservers/qwen36-gfx906/vnext-launch-runs/repro-gguf-dense27b-tp8",
      "source_lines": {
        "load": {
          "number": 4589,
          "text": "(Worker pid=227) (Worker_TP0 pid=227) INFO 06-29 12:36:09 [gpu_model_runner.py:4579] Model loading took 6.75 GiB memory and 109.957728 seconds"
        },
        "KV": {
          "number": 5245,
          "text": "(Worker pid=227) (Worker_TP0 pid=227) INFO 06-29 12:37:30 [gpu_worker.py:453] Available KV cache memory: 23.15 GiB"
        },
        "tokens": {
          "number": 5252,
          "text": "(EngineCore_DP0 pid=200) INFO 06-29 12:37:31 [kv_cache_utils.py:1314] GPU KV cache size: 379,184 tokens"
        },
        "capacity": {
          "number": 5253,
          "text": "(EngineCore_DP0 pid=200) INFO 06-29 12:37:31 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.50x"
        },
        "engine": {
          "number": 64,
          "text": "(EngineCore_DP0 pid=200) INFO 06-29 12:33:52 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-27b-f16-gguf/Qwen3.6-27B-F16.gguf', speculative_config=None, tokenizer='Qwen/Qwen3.6-27B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=gguf, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=gguf, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen3.6-27B-F16-GGUF-lmheadunquant, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': PosixPath('/runwork/debug_dump'), 'cache_dir': '/runwork/compile_cache', 'compile_cache_save_format': 'unpacked', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [4], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': True, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 4, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 33,
      "original_host": "10.0.0.30",
      "logged_model_load_delta_GiB": 6.75,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 114.586086,
      "logged_available_KV_GiB": 22.79,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 373360,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 11.32,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "37540bd9d6d3a34812dcc6e2d956c59bc7047f62aa91288bafefb2fc8773f312",
      "source_archive": "historical-recovered/host10.0.0.30-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/vnext-release-repro/cleanroom-20260629T144538Z/localaiservers/qwen36-gfx906/vnext-launch-runs/gguf-dense27b-tp8",
      "source_lines": {
        "load": {
          "number": 4589,
          "text": "(Worker pid=227) (Worker_TP0 pid=227) INFO 06-29 14:59:15 [gpu_model_runner.py:4579] Model loading took 6.75 GiB memory and 114.586086 seconds"
        },
        "KV": {
          "number": 5168,
          "text": "(Worker pid=227) (Worker_TP0 pid=227) INFO 06-29 15:02:04 [gpu_worker.py:453] Available KV cache memory: 22.79 GiB"
        },
        "tokens": {
          "number": 5175,
          "text": "(EngineCore_DP0 pid=200) INFO 06-29 15:02:04 [kv_cache_utils.py:1314] GPU KV cache size: 373,360 tokens"
        },
        "capacity": {
          "number": 5176,
          "text": "(EngineCore_DP0 pid=200) INFO 06-29 15:02:04 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.32x"
        },
        "engine": {
          "number": 64,
          "text": "(EngineCore_DP0 pid=200) INFO 06-29 14:56:55 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-27b-f16-gguf/Qwen3.6-27B-F16.gguf', speculative_config=None, tokenizer='Qwen/Qwen3.6-27B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=gguf, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=gguf, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen3.6-27B-F16-GGUF-lmheadunquant, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': PosixPath('/runwork/debug_dump'), 'cache_dir': '/runwork/compile_cache', 'compile_cache_save_format': 'unpacked', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [4], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': True, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 4, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 34,
      "original_host": "10.0.0.30",
      "logged_model_load_delta_GiB": 6.75,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 112.330588,
      "logged_available_KV_GiB": 22.79,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 373360,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 11.32,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "440fc7e6d449bf85ebc64565dfb0544de1e59b96415d3a09f31df4c5871a8a7c",
      "source_archive": "historical-recovered/host10.0.0.30-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/vnext-standalone-audit/20260629T171707Z/localaiservers/vnext-launch-runs/gguf-dense27b-tp8",
      "source_lines": {
        "load": {
          "number": 4589,
          "text": "(Worker pid=251) (Worker_TP0 pid=251) INFO 06-29 17:28:29 [gpu_model_runner.py:4579] Model loading took 6.75 GiB memory and 112.330588 seconds"
        },
        "KV": {
          "number": 5169,
          "text": "(Worker pid=251) (Worker_TP0 pid=251) INFO 06-29 17:31:23 [gpu_worker.py:453] Available KV cache memory: 22.79 GiB"
        },
        "tokens": {
          "number": 5175,
          "text": "(EngineCore_DP0 pid=224) INFO 06-29 17:31:23 [kv_cache_utils.py:1314] GPU KV cache size: 373,360 tokens"
        },
        "capacity": {
          "number": 5176,
          "text": "(EngineCore_DP0 pid=224) INFO 06-29 17:31:23 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.32x"
        },
        "engine": {
          "number": 64,
          "text": "(EngineCore_DP0 pid=224) INFO 06-29 17:26:12 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-27b-f16-gguf/Qwen3.6-27B-F16.gguf', speculative_config=None, tokenizer='Qwen/Qwen3.6-27B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=gguf, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=gguf, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen3.6-27B-F16-GGUF-lmheadunquant, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': PosixPath('/runwork/debug_dump'), 'cache_dir': '/runwork/compile_cache', 'compile_cache_save_format': 'unpacked', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [4], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': True, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 4, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 35,
      "original_host": "10.0.0.30",
      "logged_model_load_delta_GiB": 6.84,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 22.097343,
      "logged_available_KV_GiB": 22.64,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 370864,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 11.25,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "102a7ff5f97bc9e718827f1860435d52aba59065ead3318be73d7a2872aef11a",
      "source_archive": "historical-recovered/host10.0.0.30-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/vnext-release-repro/localaiservers/qwen36-gfx906/vnext-launch-runs/repro-hf-dense27b-tp8-public",
      "source_lines": {
        "load": {
          "number": 712,
          "text": "(Worker pid=202) (Worker_TP0 pid=202) INFO 06-29 13:41:17 [gpu_model_runner.py:4579] Model loading took 6.84 GiB memory and 22.097343 seconds"
        },
        "KV": {
          "number": 1271,
          "text": "(Worker pid=202) (Worker_TP0 pid=202) INFO 06-29 13:42:58 [gpu_worker.py:453] Available KV cache memory: 22.64 GiB"
        },
        "tokens": {
          "number": 1273,
          "text": "(EngineCore_DP0 pid=184) INFO 06-29 13:42:58 [kv_cache_utils.py:1314] GPU KV cache size: 370,864 tokens"
        },
        "capacity": {
          "number": 1274,
          "text": "(EngineCore_DP0 pid=184) INFO 06-29 13:42:58 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.25x"
        },
        "engine": {
          "number": 55,
          "text": "(EngineCore_DP0 pid=184) INFO 06-29 13:40:27 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-27b-hf', speculative_config=None, tokenizer='/opt/local-models/qwen36-27b-hf', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen3.6-27B, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [4], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 4, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 36,
      "original_host": "10.0.0.30",
      "logged_model_load_delta_GiB": 8.88,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 108.136458,
      "logged_available_KV_GiB": 19.91,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 521696,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 15.82,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "4eb4f84cc3c3a759f1a904f06f6727f7d5a570c87d16ff334c5f48045c2ef969",
      "source_archive": "historical-recovered/host10.0.0.30-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/vnext-release-repro/localaiservers/qwen36-gfx906/vnext-launch-runs/repro-hf-moe35b-tp8-public",
      "source_lines": {
        "load": {
          "number": 193,
          "text": "(Worker pid=189) (Worker_TP0 pid=189) INFO 06-29 14:15:32 [gpu_model_runner.py:4579] Model loading took 8.88 GiB memory and 108.136458 seconds"
        },
        "KV": {
          "number": 313,
          "text": "(Worker pid=189) (Worker_TP0 pid=189) INFO 06-29 14:17:00 [gpu_worker.py:453] Available KV cache memory: 19.91 GiB"
        },
        "tokens": {
          "number": 315,
          "text": "(EngineCore_DP0 pid=171) INFO 06-29 14:17:00 [kv_cache_utils.py:1314] GPU KV cache size: 521,696 tokens"
        },
        "capacity": {
          "number": 316,
          "text": "(EngineCore_DP0 pid=171) INFO 06-29 14:17:00 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 15.82x"
        },
        "engine": {
          "number": 33,
          "text": "(EngineCore_DP0 pid=171) INFO 06-29 14:13:13 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-35b-a3b-hf', speculative_config=None, tokenizer='/opt/local-models/qwen36-35b-a3b-hf', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen/Qwen3.6-35B-A3B, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 512, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 37,
      "original_host": "10.0.0.20",
      "logged_model_load_delta_GiB": 6.75,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 106.384137,
      "logged_available_KV_GiB": 22.79,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 373360,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 11.32,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "8db635ce1dee530b6536026905839b582cf7335807fb11229461c2333087d67b",
      "source_archive": "historical-recovered/host10.0.0.20-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/vnext-repeat-20260630T045153Z/runtime/vnext-launch-runs/20260630T050006Z-2928686/gguf-dense27b-tp8",
      "source_lines": {
        "load": {
          "number": 4596,
          "text": "(Worker pid=227) (Worker_TP0 pid=227) INFO 06-30 05:05:39 [gpu_model_runner.py:4579] Model loading took 6.75 GiB memory and 106.384137 seconds"
        },
        "KV": {
          "number": 5170,
          "text": "(Worker pid=227) (Worker_TP0 pid=227) INFO 06-30 05:08:26 [gpu_worker.py:453] Available KV cache memory: 22.79 GiB"
        },
        "tokens": {
          "number": 5174,
          "text": "(EngineCore_DP0 pid=200) INFO 06-30 05:08:26 [kv_cache_utils.py:1314] GPU KV cache size: 373,360 tokens"
        },
        "capacity": {
          "number": 5175,
          "text": "(EngineCore_DP0 pid=200) INFO 06-30 05:08:26 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.32x"
        },
        "engine": {
          "number": 63,
          "text": "(EngineCore_DP0 pid=200) INFO 06-30 05:03:28 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-27b-f16-gguf/Qwen3.6-27B-F16.gguf', speculative_config=None, tokenizer='Qwen/Qwen3.6-27B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=6a9e13bd6fc8f0983b9b99948120bc37f49c13e9, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=gguf, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=gguf, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen3.6-27B-F16-GGUF-lmheadunquant, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': PosixPath('/runwork/debug_dump'), 'cache_dir': '/runwork/compile_cache', 'compile_cache_save_format': 'unpacked', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [4], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': True, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 4, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 38,
      "original_host": "10.0.0.20",
      "logged_model_load_delta_GiB": 6.84,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 23.229114,
      "logged_available_KV_GiB": 22.64,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 370864,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 11.25,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "9e63d9b84eed3eab33372a7e7d9ccd320c5f0004a5d35eecda83a3d621f402db",
      "source_archive": "historical-recovered/host10.0.0.20-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/vnext-repeat-20260630T045153Z/runtime/vnext-launch-runs/20260630T050006Z-2928686/hf-dense27b-tp8",
      "source_lines": {
        "load": {
          "number": 712,
          "text": "(Worker pid=202) (Worker_TP0 pid=202) INFO 06-30 05:39:43 [gpu_model_runner.py:4579] Model loading took 6.84 GiB memory and 23.229114 seconds"
        },
        "KV": {
          "number": 1271,
          "text": "(Worker pid=202) (Worker_TP0 pid=202) INFO 06-30 05:41:25 [gpu_worker.py:453] Available KV cache memory: 22.64 GiB"
        },
        "tokens": {
          "number": 1273,
          "text": "(EngineCore_DP0 pid=184) INFO 06-30 05:41:25 [kv_cache_utils.py:1314] GPU KV cache size: 370,864 tokens"
        },
        "capacity": {
          "number": 1274,
          "text": "(EngineCore_DP0 pid=184) INFO 06-30 05:41:25 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.25x"
        },
        "engine": {
          "number": 55,
          "text": "(EngineCore_DP0 pid=184) INFO 06-30 05:38:53 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-27b-hf', speculative_config=None, tokenizer='/opt/local-models/qwen36-27b-hf', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen3.6-27B, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [4], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 4, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 39,
      "original_host": "10.0.0.20",
      "logged_model_load_delta_GiB": 8.88,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 115.559999,
      "logged_available_KV_GiB": 19.91,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 521696,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 15.82,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "6e661b86c7832729f1ccff5efa87579d419dd3771f3ed7e6ea42e1105ddfb44a",
      "source_archive": "historical-recovered/host10.0.0.20-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/vnext-repeat-20260630T045153Z/runtime/vnext-launch-runs/20260630T050006Z-2928686/hf-moe35b-tp8",
      "source_lines": {
        "load": {
          "number": 193,
          "text": "(Worker pid=189) (Worker_TP0 pid=189) INFO 06-30 06:13:45 [gpu_model_runner.py:4579] Model loading took 8.88 GiB memory and 115.559999 seconds"
        },
        "KV": {
          "number": 313,
          "text": "(Worker pid=189) (Worker_TP0 pid=189) INFO 06-30 06:15:07 [gpu_worker.py:453] Available KV cache memory: 19.91 GiB"
        },
        "tokens": {
          "number": 315,
          "text": "(EngineCore_DP0 pid=171) INFO 06-30 06:15:07 [kv_cache_utils.py:1314] GPU KV cache size: 521,696 tokens"
        },
        "capacity": {
          "number": 316,
          "text": "(EngineCore_DP0 pid=171) INFO 06-30 06:15:07 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 15.82x"
        },
        "engine": {
          "number": 33,
          "text": "(EngineCore_DP0 pid=171) INFO 06-30 06:11:18 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-35b-a3b-hf', speculative_config=None, tokenizer='/opt/local-models/qwen36-35b-a3b-hf', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen/Qwen3.6-35B-A3B, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 512, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 40,
      "original_host": "10.0.0.30",
      "logged_model_load_delta_GiB": 6.75,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 115.568181,
      "logged_available_KV_GiB": 22.79,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 373360,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 11.32,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "8e5636e5ce75ea4e080735843d07126b395cbb4f4b8ea2928b3f6e92369a61ae",
      "source_archive": "historical-recovered/host10.0.0.30-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/vnext-release-repro/public-staging-20260629/runtime-full-current-20260630T111241Z/vnext-launch-runs/20260630T111242Z-2834957/gguf-dense27b-tp8",
      "source_lines": {
        "load": {
          "number": 4588,
          "text": "(Worker pid=227) (Worker_TP0 pid=227) INFO 06-30 11:18:48 [gpu_model_runner.py:4579] Model loading took 6.75 GiB memory and 115.568181 seconds"
        },
        "KV": {
          "number": 5168,
          "text": "(Worker pid=227) (Worker_TP0 pid=227) INFO 06-30 11:21:37 [gpu_worker.py:453] Available KV cache memory: 22.79 GiB"
        },
        "tokens": {
          "number": 5174,
          "text": "(EngineCore_DP0 pid=200) INFO 06-30 11:21:37 [kv_cache_utils.py:1314] GPU KV cache size: 373,360 tokens"
        },
        "capacity": {
          "number": 5175,
          "text": "(EngineCore_DP0 pid=200) INFO 06-30 11:21:37 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.32x"
        },
        "engine": {
          "number": 63,
          "text": "(EngineCore_DP0 pid=200) INFO 06-30 11:16:27 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-27b-f16-gguf/Qwen3.6-27B-F16.gguf', speculative_config=None, tokenizer='Qwen/Qwen3.6-27B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=6a9e13bd6fc8f0983b9b99948120bc37f49c13e9, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=gguf, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=gguf, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen3.6-27B-F16-GGUF-lmheadunquant, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': PosixPath('/runwork/debug_dump'), 'cache_dir': '/runwork/compile_cache', 'compile_cache_save_format': 'unpacked', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [4], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': True, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 4, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 41,
      "original_host": "10.0.0.30",
      "logged_model_load_delta_GiB": 6.84,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 24.431786,
      "logged_available_KV_GiB": 22.64,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 370864,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 11.25,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "31b012b6fd4429cc642f68c73f43900399682da4ad3cc8254abae19f76ce393f",
      "source_archive": "historical-recovered/host10.0.0.30-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/vnext-release-repro/public-staging-20260629/runtime-full-current-20260630T111241Z/vnext-launch-runs/20260630T111242Z-2834957/hf-dense27b-tp8",
      "source_lines": {
        "load": {
          "number": 712,
          "text": "(Worker pid=202) (Worker_TP0 pid=202) INFO 06-30 11:53:09 [gpu_model_runner.py:4579] Model loading took 6.84 GiB memory and 24.431786 seconds"
        },
        "KV": {
          "number": 1270,
          "text": "(Worker pid=202) (Worker_TP0 pid=202) INFO 06-30 11:54:49 [gpu_worker.py:453] Available KV cache memory: 22.64 GiB"
        },
        "tokens": {
          "number": 1273,
          "text": "(EngineCore_DP0 pid=184) INFO 06-30 11:54:49 [kv_cache_utils.py:1314] GPU KV cache size: 370,864 tokens"
        },
        "capacity": {
          "number": 1274,
          "text": "(EngineCore_DP0 pid=184) INFO 06-30 11:54:49 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.25x"
        },
        "engine": {
          "number": 55,
          "text": "(EngineCore_DP0 pid=184) INFO 06-30 11:52:18 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-27b-hf', speculative_config=None, tokenizer='/opt/local-models/qwen36-27b-hf', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen3.6-27B, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [4], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 4, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 42,
      "original_host": "10.0.0.30",
      "logged_model_load_delta_GiB": 8.88,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 110.381889,
      "logged_available_KV_GiB": 19.91,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 521696,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 15.82,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "537cbbf045673c0c5d8d0ae112aca2b44ca8cf1d8a8055c940cdd6d0e50761ed",
      "source_archive": "historical-recovered/host10.0.0.30-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/vnext-release-repro/public-staging-20260629/runtime-full-current-20260630T111241Z/vnext-launch-runs/20260630T111242Z-2834957/hf-moe35b-tp8",
      "source_lines": {
        "load": {
          "number": 193,
          "text": "(Worker pid=189) (Worker_TP0 pid=189) INFO 06-30 12:26:46 [gpu_model_runner.py:4579] Model loading took 8.88 GiB memory and 110.381889 seconds"
        },
        "KV": {
          "number": 311,
          "text": "(Worker pid=189) (Worker_TP0 pid=189) INFO 06-30 12:28:16 [gpu_worker.py:453] Available KV cache memory: 19.91 GiB"
        },
        "tokens": {
          "number": 315,
          "text": "(EngineCore_DP0 pid=171) INFO 06-30 12:28:16 [kv_cache_utils.py:1314] GPU KV cache size: 521,696 tokens"
        },
        "capacity": {
          "number": 316,
          "text": "(EngineCore_DP0 pid=171) INFO 06-30 12:28:16 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 15.82x"
        },
        "engine": {
          "number": 33,
          "text": "(EngineCore_DP0 pid=171) INFO 06-30 12:24:26 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-35b-a3b-hf', speculative_config=None, tokenizer='/opt/local-models/qwen36-35b-a3b-hf', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen/Qwen3.6-35B-A3B, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 512, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 43,
      "original_host": "10.0.0.30",
      "logged_model_load_delta_GiB": 6.75,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 108.890125,
      "logged_available_KV_GiB": 22.79,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 373360,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 11.32,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "a9babfca90bf4dc23965294f0abf27b401f6228b3748e1864c5814dd2d3dc3c4",
      "source_archive": "historical-recovered/host10.0.0.30-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/vnext-release-repro/public-staging-20260629/runtime-full-current-proof/vnext-launch-runs/20260630T130329Z-2951956/gguf-dense27b-tp8",
      "source_lines": {
        "load": {
          "number": 4588,
          "text": "(Worker pid=227) (Worker_TP0 pid=227) INFO 06-30 13:09:21 [gpu_model_runner.py:4579] Model loading took 6.75 GiB memory and 108.890125 seconds"
        },
        "KV": {
          "number": 5163,
          "text": "(Worker pid=227) (Worker_TP0 pid=227) INFO 06-30 13:12:06 [gpu_worker.py:453] Available KV cache memory: 22.79 GiB"
        },
        "tokens": {
          "number": 5174,
          "text": "(EngineCore_DP0 pid=200) INFO 06-30 13:12:08 [kv_cache_utils.py:1314] GPU KV cache size: 373,360 tokens"
        },
        "capacity": {
          "number": 5175,
          "text": "(EngineCore_DP0 pid=200) INFO 06-30 13:12:08 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.32x"
        },
        "engine": {
          "number": 63,
          "text": "(EngineCore_DP0 pid=200) INFO 06-30 13:07:07 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-27b-f16-gguf/Qwen3.6-27B-F16.gguf', speculative_config=None, tokenizer='Qwen/Qwen3.6-27B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=6a9e13bd6fc8f0983b9b99948120bc37f49c13e9, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=gguf, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=gguf, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen3.6-27B-F16-GGUF-lmheadunquant, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': PosixPath('/runwork/debug_dump'), 'cache_dir': '/runwork/compile_cache', 'compile_cache_save_format': 'unpacked', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [4], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': True, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 4, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 44,
      "original_host": "10.0.0.30",
      "logged_model_load_delta_GiB": 6.84,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 23.129179,
      "logged_available_KV_GiB": 22.64,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 370864,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 11.25,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "b5013067f3d140ab979a82911c5da3b6999e4ab982bb451aba02c56a7eb79a3a",
      "source_archive": "historical-recovered/host10.0.0.30-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/vnext-release-repro/public-staging-20260629/runtime-full-current-proof/vnext-launch-runs/20260630T130329Z-2951956/hf-dense27b-tp8",
      "source_lines": {
        "load": {
          "number": 712,
          "text": "(Worker pid=202) (Worker_TP0 pid=202) INFO 06-30 13:43:37 [gpu_model_runner.py:4579] Model loading took 6.84 GiB memory and 23.129179 seconds"
        },
        "KV": {
          "number": 1269,
          "text": "(Worker pid=202) (Worker_TP0 pid=202) INFO 06-30 13:45:17 [gpu_worker.py:453] Available KV cache memory: 22.64 GiB"
        },
        "tokens": {
          "number": 1273,
          "text": "(EngineCore_DP0 pid=184) INFO 06-30 13:45:17 [kv_cache_utils.py:1314] GPU KV cache size: 370,864 tokens"
        },
        "capacity": {
          "number": 1274,
          "text": "(EngineCore_DP0 pid=184) INFO 06-30 13:45:17 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 11.25x"
        },
        "engine": {
          "number": 55,
          "text": "(EngineCore_DP0 pid=184) INFO 06-30 13:42:48 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-27b-hf', speculative_config=None, tokenizer='/opt/local-models/qwen36-27b-hf', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen3.6-27B, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [4], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 4, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    },
    {
      "row": 45,
      "original_host": "10.0.0.30",
      "logged_model_load_delta_GiB": 8.88,
      "model_load_report_rank": 0,
      "logged_model_load_seconds": 116.951902,
      "logged_available_KV_GiB": 19.91,
      "KV_memory_report_rank": 0,
      "logged_GPU_KV_tokens": 521696,
      "logged_context_tokens": 131072,
      "logged_context_capacity_x": 15.82,
      "engine_FP16_TP8_context131072_MTPoff": true,
      "source_log_sha256": "5fb63afa234d5088372f07d9632c05c1e4329772bf04a0e3c8fa2fff842b58a7",
      "source_archive": "historical-recovered/host10.0.0.30-original-evidence.tar.gz",
      "original_launch_path": "/usr/share/ollama/vnext-release-repro/public-staging-20260629/runtime-full-current-proof/vnext-launch-runs/20260630T130329Z-2951956/hf-moe35b-tp8",
      "source_lines": {
        "load": {
          "number": 193,
          "text": "(Worker pid=189) (Worker_TP0 pid=189) INFO 06-30 14:17:32 [gpu_model_runner.py:4579] Model loading took 8.88 GiB memory and 116.951902 seconds"
        },
        "KV": {
          "number": 307,
          "text": "(Worker pid=189) (Worker_TP0 pid=189) INFO 06-30 14:18:54 [gpu_worker.py:453] Available KV cache memory: 19.91 GiB"
        },
        "tokens": {
          "number": 315,
          "text": "(EngineCore_DP0 pid=171) INFO 06-30 14:18:55 [kv_cache_utils.py:1314] GPU KV cache size: 521,696 tokens"
        },
        "capacity": {
          "number": 316,
          "text": "(EngineCore_DP0 pid=171) INFO 06-30 14:18:55 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 15.82x"
        },
        "engine": {
          "number": 33,
          "text": "(EngineCore_DP0 pid=171) INFO 06-30 14:15:05 [core.py:101] Initializing a V1 LLM engine (v0.0.0+gfx906) with config: model='/opt/local-models/qwen36-35b-a3b-hf', speculative_config=None, tokenizer='/opt/local-models/qwen36-35b-a3b-hf', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=8, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=Qwen/Qwen3.6-35B-A3B, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['+sparse_attn_indexer', 'none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_endpoints': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False, 'fuse_rope_kvcache': False}, 'max_cudagraph_capture_size': 512, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}"
        }
      },
      "limits": "Rounded rank-specific engine load delta and available KV budget, not exact tensor-byte sums, physical VRAM usage or proof that every rank has the same footprint. Logged grouped KV tokens/concurrency do not demonstrate a full-context request. Original physical VRAM usage remains unavailable."
    }
  ],
  "source": "Authenticated original launch logs already bound to the original response intervals.",
  "physical_VRAM_usage_recovered": false,
  "new_GPU_measurements": 0
}
