state: generation 6744 (cycle)

2026-09-13 13:45:02 +00:00
parent 6c858a2a51
commit ec6620b872
10 changed files with 1930 additions and 1981 deletions
--- a/.modelhub_state/architecture_compatibility_blacklist.json
+++ b/.modelhub_state/architecture_compatibility_blacklist.json
@@ -1475,7 +1475,7 @@
      "taskType": "text-generation"
    }
  },
-  "generatedAt": "2026-09-13T13:42:18.224764+00:00",
+  "generatedAt": "2026-09-13T13:45:01.825834+00:00",
  "summary": {
    "activeBlockCount": 74,
    "byGpuFramework": {
--- a/.modelhub_state/architecture_history_backfill.json
+++ b/.modelhub_state/architecture_history_backfill.json
@@ -75,7 +75,7 @@
    "7": {
      "complete": false,
      "lastError": "ModelHubAPIError: 系统错误",
-      "listingErrors": 488,
+      "listingErrors": 489,
      "nextPage": 1,
      "recordsScanned": 0,
      "uniqueRecords": 0
@@ -102,12 +102,12 @@
  "cutoffAt": "2026-09-04T03:55:51.365685+00:00",
  "failureLogsInspected": 0,
  "mode": "incremental_decision_only",
-  "nextAccountIndex": 7,
+  "nextAccountIndex": 8,
  "recordsScanned": 0,
  "seenTaskIds": [],
  "startedAt": "2026-09-04T03:55:51.365685+00:00",
  "terminalRecords": 0,
  "uniqueRecords": 0,
-  "updatedAt": "2026-09-13T13:42:18.201802+00:00",
+  "updatedAt": "2026-09-13T13:45:01.799157+00:00",
  "version": 1
 }
--- a/.modelhub_state/market_intelligence.json
+++ b/.modelhub_state/market_intelligence.json
@@ -416,7 +416,7 @@
    }
  },
  "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-13T13:40:48.503357+00:00",
+  "generatedAt": "2026-09-13T13:43:37.818868+00:00",
  "gpuStats": {
    "Ascend_910-b3": {
      "available": true,
--- a/.modelhub_state/official_capabilities.json
+++ b/.modelhub_state/official_capabilities.json
--- a/.modelhub_state/outcome_checkpoint.json
+++ b/.modelhub_state/outcome_checkpoint.json
@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-13T13:17:31.378518+00:00",
-  "lastSyncTime": "2026-09-13T13:17:31.149592+00:00",
+  "generatedAt": "2026-09-13T13:43:30.341463+00:00",
+  "lastSyncTime": "2026-09-13T13:43:30.144236+00:00",
  "recentLimit": 300,
  "report": {
    "architectureCompatibilityBlocks": {
@@ -2011,11 +2011,11 @@
        "decisionSuccessRate": 0.0,
        "decisionTotal": 1,
        "failureBreakdown": {
-          "ambiguous_runtime": 37,
+          "ambiguous_runtime": 38,
          "memory_capacity": 1,
          "验证失败": 22
        },
-        "failureCount": 60,
+        "failureCount": 61,
        "failureRate": 1.0,
        "framework": "unknown",
        "pendingCount": 0,
@@ -2025,8 +2025,8 @@
        "successRate": 0.0,
        "targetGpu": "Kunlunxin_p-800",
        "taskType": "text-generation",
-        "total": 60,
-        "unresolvedFailureCount": 59
+        "total": 61,
+        "unresolvedFailureCount": 60
      },
      "Kunlunxin_p-800|unknown|visual-multi-modal": {
        "attributableFailureCount": 0,
@@ -2489,7 +2489,7 @@
        "decisionSuccessRate": 0.2609,
        "decisionTotal": 207,
        "failureBreakdown": {
-          "ambiguous_runtime": 142,
+          "ambiguous_runtime": 143,
          "backend_operator": 4,
          "framework_architecture_unsupported": 98,
          "memory_capacity": 5,
@@ -2499,15 +2499,15 @@
          "参数/模板问题": 61,
          "验证失败": 673
        },
-        "failureCount": 1030,
+        "failureCount": 1031,
        "failureRate": 0.9502,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 1,
        "successCount": 54,
        "successRate": 0.0498,
-        "total": 1084,
-        "unresolvedFailureCount": 876
+        "total": 1085,
+        "unresolvedFailureCount": 877
      },
      "vllm": {
        "attributableFailureCount": 297,
@@ -2638,7 +2638,7 @@
        "unresolvedFailureCount": 1
      }
    },
-    "generatedAt": "2026-09-13T13:17:31.373858+00:00",
+    "generatedAt": "2026-09-13T13:43:30.337302+00:00",
    "gpuSummaries": {
      "Ascend_910-b3": {
        "attributableFailureCount": 31,
@@ -2831,20 +2831,20 @@
        "decisionSuccessRate": 0.0,
        "decisionTotal": 1,
        "failureBreakdown": {
-          "ambiguous_runtime": 72,
+          "ambiguous_runtime": 73,
          "memory_capacity": 1,
          "参数/模板问题": 1,
          "验证失败": 23
        },
-        "failureCount": 97,
+        "failureCount": 98,
        "failureRate": 1.0,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
-        "total": 97,
-        "unresolvedFailureCount": 96
+        "total": 98,
+        "unresolvedFailureCount": 97
      },
      "MetaX_c-500": {
        "attributableFailureCount": 54,
@@ -4775,13 +4775,13 @@
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
-          "ambiguous_runtime": 8
+          "ambiguous_runtime": 9
        },
-        "failureCount": 8,
+        "failureCount": 9,
        "failureRate": 1.0,
        "framework": "unknown",
        "lastPlatformFailureAt": null,
-        "lastTerminalAt": "2026-09-13T10:05:37.717736+00:00",
+        "lastTerminalAt": "2026-09-13T13:43:30.144198+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
@@ -4789,8 +4789,8 @@
        "successRate": 0.0,
        "targetGpu": "Kunlunxin_p-800",
        "taskType": "text-generation",
-        "total": 8,
-        "unresolvedFailureCount": 8
+        "total": 9,
+        "unresolvedFailureCount": 9
      },
      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
        "attributableFailureCount": 0,
@@ -4976,31 +4976,6 @@
        "total": 5,
        "unresolvedFailureCount": 1
      },
-      "Vastai_va16|vllm_fix_tokenizer|text-generation": {
-        "attributableFailureCount": 0,
-        "consecutiveFailures": 0,
-        "consecutivePlatformFailures": 0,
-        "decisionFailureRate": 0.0,
-        "decisionSuccessRate": 0.0,
-        "decisionTotal": 0,
-        "failureBreakdown": {
-          "ambiguous_runtime": 1
-        },
-        "failureCount": 1,
-        "failureRate": 1.0,
-        "framework": "vllm_fix_tokenizer",
-        "lastPlatformFailureAt": null,
-        "lastTerminalAt": "2026-09-10T16:44:50.902809+00:00",
-        "pendingCount": 0,
-        "pendingRate": 0.0,
-        "platformFailureCount": 0,
-        "successCount": 0,
-        "successRate": 0.0,
-        "targetGpu": "Vastai_va16",
-        "taskType": "text-generation",
-        "total": 1,
-        "unresolvedFailureCount": 1
-      },
      "Vastai_va16|vllm|text-generation": {
        "attributableFailureCount": 5,
        "consecutiveFailures": 5,
@@ -5132,31 +5107,6 @@
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 1
-      },
-      "Vastai_va16|vllm_fix_tokenizer|text-generation|minicpm|none": {
-        "attributableFailureCount": 0,
-        "consecutiveFailures": 0,
-        "decisionFailureRate": 0.0,
-        "decisionSuccessRate": 0.0,
-        "decisionTotal": 0,
-        "failureBreakdown": {
-          "ambiguous_runtime": 1
-        },
-        "failureCount": 1,
-        "failureRate": 1.0,
-        "framework": "vllm_fix_tokenizer",
-        "lastTerminalAt": "2026-09-10T16:44:50.902809+00:00",
-        "modelType": "minicpm",
-        "pendingCount": 0,
-        "pendingRate": 0.0,
-        "platformFailureCount": 0,
-        "quantizationMethod": "none",
-        "successCount": 0,
-        "successRate": 0.0,
-        "targetGpu": "Vastai_va16",
-        "taskType": "text-generation",
-        "total": 1,
-        "unresolvedFailureCount": 1
      }
    },
    "sizedProfileCombinationStats": {
@@ -7507,15 +7457,15 @@
        "unresolvedFailureCount": 0
      }
    },
-    "terminalRecords": 1773,
-    "totalRecords": 1860,
+    "terminalRecords": 1774,
+    "totalRecords": 1861,
    "totals": {
      "attributableFailureCount": 518,
      "decisionFailureRate": 0.8977,
      "decisionSuccessRate": 0.1023,
      "decisionTotal": 577,
      "failureBreakdown": {
-        "ambiguous_runtime": 416,
+        "ambiguous_runtime": 417,
        "backend_operator": 43,
        "framework_architecture_unsupported": 327,
        "memory_capacity": 11,
@@ -7527,15 +7477,15 @@
        "参数/模板问题": 103,
        "验证失败": 673
      },
-      "failureCount": 1714,
+      "failureCount": 1715,
      "failureRate": 0.9667,
      "pendingCount": 0,
      "pendingRate": 0.0,
      "platformFailureCount": 4,
      "successCount": 59,
      "successRate": 0.0333,
-      "total": 1773,
-      "unresolvedFailureCount": 1192
+      "total": 1774,
+      "unresolvedFailureCount": 1193
    },
    "warnings": [
      "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -7572,6 +7522,6 @@
    ]
  },
  "storageMode": "decision_state_only",
-  "summarizedRecords": 1860,
+  "summarizedRecords": 1861,
  "version": 1
 }
--- a/.modelhub_state/recent_outcomes.jsonl
+++ b/.modelhub_state/recent_outcomes.jsonl
@@ -1,3 +1,4 @@
+{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T13:43:30.144198+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T13:43:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4332459", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-13T13:17:31.149556+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T13:11:21+00:00", "targetGpu": "Biren_166m", "taskId": "4349465", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T10:05:37.717736+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T09:59:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4560059", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-13T09:40:23.641563+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T09:33:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4557415", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
 {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-09T15:39:07.233616+00:00", "modelId": "mlx-community/Ornith-1.0-9B-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T15:33:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079339", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T14:59:28.333305+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T14:59:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4477956", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-09T14:59:28.333331+00:00", "modelId": "ornith-ai/Ornith-1.5-9B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T14:55:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332980", "taskType": "text-generation", "verifyResult": -1}
-{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T16:44:50.902809+00:00", "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634920, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T12:30:12.314907+00:00", "targetGpu": "Vastai_va16", "taskId": "4740401", "taskType": "text-generation", "verifyResult": -1}
--- a/.modelhub_state/recovery_active_tasks.jsonl
+++ b/.modelhub_state/recovery_active_tasks.jsonl
--- a/.modelhub_state/recovery_intents.jsonl
+++ b/.modelhub_state/recovery_intents.jsonl