state: generation 6900 (cycle)

2026-09-13 21:48:23 +00:00
parent 30ccccab55
commit 21c88ea5c2
9 changed files with 1937 additions and 1935 deletions
--- a/.modelhub_state/architecture_compatibility_blacklist.json
+++ b/.modelhub_state/architecture_compatibility_blacklist.json
@@ -1494,7 +1494,7 @@
      "taskType": "text-generation"
    }
  },
-  "generatedAt": "2026-09-13T21:44:40.896730+00:00",
+  "generatedAt": "2026-09-13T21:48:22.537469+00:00",
  "summary": {
    "activeBlockCount": 75,
    "byGpuFramework": {
--- a/.modelhub_state/architecture_history_backfill.json
+++ b/.modelhub_state/architecture_history_backfill.json
@@ -11,7 +11,7 @@
    "1": {
      "complete": false,
      "lastError": "ModelHubAPIError: 系统错误",
-      "listingErrors": 501,
+      "listingErrors": 502,
      "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": 1,
+  "nextAccountIndex": 2,
  "recordsScanned": 0,
  "seenTaskIds": [],
  "startedAt": "2026-09-04T03:55:51.365685+00:00",
  "terminalRecords": 0,
  "uniqueRecords": 0,
-  "updatedAt": "2026-09-13T21:44:40.872801+00:00",
+  "updatedAt": "2026-09-13T21:48:22.514325+00:00",
  "version": 1
 }
--- a/.modelhub_state/market_intelligence.json
+++ b/.modelhub_state/market_intelligence.json
@@ -1,8 +1,8 @@
 {
-  "communityAttemptedAt": "2026-09-13T21:30:23.179573+00:00",
+  "communityAttemptedAt": "2026-09-13T21:45:50.305575+00:00",
  "communityError": null,
  "communitySample": {},
-  "communityUpdatedAt": "2026-09-13T21:30:23.179573+00:00",
+  "communityUpdatedAt": "2026-09-13T21:45:50.305575+00:00",
  "frameworkAttemptedAt": "2026-09-13T18:45:49.870085+00:00",
  "frameworkError": null,
  "frameworkStats": {
@@ -416,7 +416,7 @@
    }
  },
  "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-13T21:42:54.736785+00:00",
+  "generatedAt": "2026-09-13T21:45:50.305575+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": "2026-09-13T21:36:16.950711+00:00",
-  "lastSyncTime": "2026-09-13T21:36:16.709712+00:00",
+  "generatedAt": "2026-09-13T21:45:41.906553+00:00",
+  "lastSyncTime": "2026-09-13T21:45:41.613474+00:00",
  "recentLimit": 300,
  "report": {
    "architectureCompatibilityBlocks": {
@@ -1981,7 +1981,7 @@
        "decisionSuccessRate": 0.1364,
        "decisionTotal": 110,
        "failureBreakdown": {
-          "ambiguous_runtime": 22,
+          "ambiguous_runtime": 23,
          "framework_architecture_unsupported": 52,
          "memory_capacity": 1,
          "model_load": 42,
@@ -1989,18 +1989,18 @@
          "参数/模板问题": 2,
          "验证失败": 47
        },
-        "failureCount": 167,
-        "failureRate": 0.9176,
+        "failureCount": 168,
+        "failureRate": 0.918,
        "framework": "unknown",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 1,
        "successCount": 15,
-        "successRate": 0.0824,
+        "successRate": 0.082,
        "targetGpu": "Iluvatar_mrv-100",
        "taskType": "text-generation",
-        "total": 182,
-        "unresolvedFailureCount": 71
+        "total": 183,
+        "unresolvedFailureCount": 72
      },
      "Iluvatar_mrv-100|vllm|text-generation": {
        "attributableFailureCount": 3,
@@ -2509,7 +2509,7 @@
        "decisionSuccessRate": 0.2584,
        "decisionTotal": 209,
        "failureBreakdown": {
-          "ambiguous_runtime": 144,
+          "ambiguous_runtime": 145,
          "backend_operator": 4,
          "framework_architecture_unsupported": 99,
          "memory_capacity": 5,
@@ -2519,15 +2519,15 @@
          "参数/模板问题": 61,
          "验证失败": 673
        },
-        "failureCount": 1034,
+        "failureCount": 1035,
        "failureRate": 0.9504,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 1,
        "successCount": 54,
        "successRate": 0.0496,
-        "total": 1088,
-        "unresolvedFailureCount": 878
+        "total": 1089,
+        "unresolvedFailureCount": 879
      },
      "vllm": {
        "attributableFailureCount": 302,
@@ -2658,7 +2658,7 @@
        "unresolvedFailureCount": 1
      }
    },
-    "generatedAt": "2026-09-13T21:36:16.946722+00:00",
+    "generatedAt": "2026-09-13T21:45:41.901663+00:00",
    "gpuSummaries": {
      "Ascend_910-b3": {
        "attributableFailureCount": 31,
@@ -2827,7 +2827,7 @@
        "decisionSuccessRate": 0.1327,
        "decisionTotal": 113,
        "failureBreakdown": {
-          "ambiguous_runtime": 22,
+          "ambiguous_runtime": 23,
          "framework_architecture_unsupported": 54,
          "memory_capacity": 1,
          "model_load": 43,
@@ -2835,15 +2835,15 @@
          "参数/模板问题": 2,
          "验证失败": 47
        },
-        "failureCount": 170,
-        "failureRate": 0.9189,
+        "failureCount": 171,
+        "failureRate": 0.9194,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 1,
        "successCount": 15,
-        "successRate": 0.0811,
-        "total": 185,
-        "unresolvedFailureCount": 71
+        "successRate": 0.0806,
+        "total": 186,
+        "unresolvedFailureCount": 72
      },
      "Kunlunxin_p-800": {
        "attributableFailureCount": 1,
@@ -4855,22 +4855,22 @@
        "unresolvedFailureCount": 1
      },
      "Iluvatar_mrv-100|unknown|text-generation": {
-        "attributableFailureCount": 11,
+        "attributableFailureCount": 10,
        "consecutiveFailures": 3,
        "consecutivePlatformFailures": 0,
-        "decisionFailureRate": 0.6875,
-        "decisionSuccessRate": 0.3125,
-        "decisionTotal": 16,
+        "decisionFailureRate": 0.6667,
+        "decisionSuccessRate": 0.3333,
+        "decisionTotal": 15,
        "failureBreakdown": {
-          "ambiguous_runtime": 4,
+          "ambiguous_runtime": 5,
          "framework_architecture_unsupported": 4,
-          "model_load": 7
+          "model_load": 6
        },
        "failureCount": 15,
        "failureRate": 0.75,
        "framework": "unknown",
        "lastPlatformFailureAt": null,
-        "lastTerminalAt": "2026-09-13T21:36:16.709712+00:00",
+        "lastTerminalAt": "2026-09-13T21:45:41.613474+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
@@ -4879,7 +4879,7 @@
        "targetGpu": "Iluvatar_mrv-100",
        "taskType": "text-generation",
        "total": 20,
-        "unresolvedFailureCount": 4
+        "unresolvedFailureCount": 5
      },
      "Kunlunxin_p-800|unknown|text-generation": {
        "attributableFailureCount": 0,
@@ -7692,15 +7692,15 @@
        "unresolvedFailureCount": 0
      }
    },
-    "terminalRecords": 1789,
-    "totalRecords": 1882,
+    "terminalRecords": 1790,
+    "totalRecords": 1883,
    "totals": {
      "attributableFailureCount": 530,
      "decisionFailureRate": 0.8998,
      "decisionSuccessRate": 0.1002,
      "decisionTotal": 589,
      "failureBreakdown": {
-        "ambiguous_runtime": 418,
+        "ambiguous_runtime": 419,
        "backend_operator": 43,
        "framework_architecture_unsupported": 335,
        "memory_capacity": 12,
@@ -7712,15 +7712,15 @@
        "参数/模板问题": 103,
        "验证失败": 673
      },
-      "failureCount": 1730,
+      "failureCount": 1731,
      "failureRate": 0.967,
      "pendingCount": 0,
      "pendingRate": 0.0,
      "platformFailureCount": 6,
      "successCount": 59,
      "successRate": 0.033,
-      "total": 1789,
-      "unresolvedFailureCount": 1194
+      "total": 1790,
+      "unresolvedFailureCount": 1195
    },
    "warnings": [
      "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -7758,6 +7758,6 @@
    ]
  },
  "storageMode": "decision_state_only",
-  "summarizedRecords": 1882,
+  "summarizedRecords": 1883,
  "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": "2026-09-13T21:45:41.613474+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:39:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4559290", "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": "2026-09-13T21:36:16.709712+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:33:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523305", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 64.0, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-13T21:27:15.041934+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:21:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4581573", "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_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mellum"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T21:09:24.912761+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4152538", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-09T18:28:27.522346+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:21:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610358", "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", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-09T18:09:45.834676+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:05:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4592383", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T18:09:45.834698+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471904", "taskType": "text-generation", "verifyResult": -1}
-{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T18:09:45.834707+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471907", "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