state: generation 11714 (cycle_no_slots)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -2850,7 +2850,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-21T20:27:40.558645+00:00",
+  "generatedAt": "2026-09-21T20:29:48.864519+00:00",
   "summary": {
     "activeBlockCount": 143,
     "byGpuFramework": {

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-21T20:22:54.503263+00:00",
+  "generatedAt": "2026-09-21T20:29:48.794296+00:00",
-  "lastSyncTime": "2026-09-21T20:22:53.859295+00:00",
+  "lastSyncTime": "2026-09-21T20:29:48.458102+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -2977,24 +2977,24 @@
         "decisionSuccessRate": 0.0625,
         "decisionTotal": 32,
         "failureBreakdown": {
-          "ambiguous_runtime": 34,
+          "ambiguous_runtime": 35,
           "context_length": 3,
           "framework_architecture_unsupported": 26,
           "memory_capacity": 1,
           "参数/模板问题": 8
         },
-        "failureCount": 72,
+        "failureCount": 73,
-        "failureRate": 0.973,
+        "failureRate": 0.9733,
         "framework": "vllm_tokenizer_patch",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 2,
-        "successRate": 0.027,
+        "successRate": 0.0267,
         "targetGpu": "Ascend_910-b3",
         "taskType": "text-generation",
-        "total": 74,
+        "total": 75,
-        "unresolvedFailureCount": 42
+        "unresolvedFailureCount": 43
       },
       "Ascend_910-b3|vllm|text-generation": {
         "attributableFailureCount": 68,
@@ -5657,7 +5657,7 @@
         "decisionSuccessRate": 0.0253,
         "decisionTotal": 79,
         "failureBreakdown": {
-          "ambiguous_runtime": 83,
+          "ambiguous_runtime": 84,
           "backend_operator": 1,
           "context_length": 3,
           "framework_architecture_unsupported": 66,
@@ -5668,18 +5668,18 @@
           "tokenizer_compatibility": 1,
           "参数/模板问题": 27
         },
-        "failureCount": 188,
+        "failureCount": 189,
         "failureRate": 0.9895,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 2,
         "successRate": 0.0105,
-        "total": 190,
+        "total": 191,
-        "unresolvedFailureCount": 110
+        "unresolvedFailureCount": 111
       }
     },
-    "generatedAt": "2026-09-21T20:22:54.492261+00:00",
+    "generatedAt": "2026-09-21T20:29:48.783719+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 99,
@@ -5687,7 +5687,7 @@
         "decisionSuccessRate": 0.161,
         "decisionTotal": 118,
         "failureBreakdown": {
-          "ambiguous_runtime": 95,
+          "ambiguous_runtime": 96,
           "context_length": 3,
           "framework_architecture_unsupported": 91,
           "memory_capacity": 2,
@@ -5697,15 +5697,15 @@
           "日志缺失": 3,
           "验证失败": 27
         },
-        "failureCount": 263,
+        "failureCount": 264,
-        "failureRate": 0.9326,
+        "failureRate": 0.9329,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 19,
-        "successRate": 0.0674,
+        "successRate": 0.0671,
-        "total": 282,
+        "total": 283,
-        "unresolvedFailureCount": 164
+        "unresolvedFailureCount": 165
       },
       "Ascend_910-b4": {
         "attributableFailureCount": 322,
@@ -6879,9 +6879,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 2
+          "ambiguous_runtime": 3
         },
-        "failureCount": 2,
+        "failureCount": 3,
         "failureRate": 1.0,
         "framework": "vllm_tokenizer_patch",
         "modelType": "starcoder2",
@@ -6893,8 +6893,8 @@
         "successRate": 0.0,
         "targetGpu": "Ascend_910-b3",
         "taskType": "text-generation",
-        "total": 2,
+        "total": 3,
-        "unresolvedFailureCount": 2
+        "unresolvedFailureCount": 3
       },
       "Ascend_910-b3|vllm|text-generation|bailing_hybrid|none": {
         "attributableFailureCount": 1,
@@ -22568,6 +22568,30 @@
         "total": 1,
         "unresolvedFailureCount": 1
       },
+      "Ascend_910-b3|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|34": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_tokenizer_patch",
+        "loadSizeLog2Bucket": 34,
+        "modelType": "starcoder2",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "compressed-tensors",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Ascend_910-b3",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
       "Ascend_910-b3|vllm|text-generation|bailing_hybrid|none|34": {
         "attributableFailureCount": 1,
         "decisionFailureRate": 1.0,
@@ -37956,15 +37980,15 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 16403,
+    "terminalRecords": 16404,
-    "totalRecords": 16597,
+    "totalRecords": 16598,
     "totals": {
       "attributableFailureCount": 5918,
       "decisionFailureRate": 0.8622,
       "decisionSuccessRate": 0.1378,
       "decisionTotal": 6864,
       "failureBreakdown": {
-        "ambiguous_runtime": 4030,
+        "ambiguous_runtime": 4031,
         "architecture_compatibility": 212,
         "attention_backend": 1,
         "backend_operator": 104,
@@ -37980,31 +38004,31 @@
         "日志缺失": 719,
         "验证失败": 674
       },
-      "failureCount": 15457,
+      "failureCount": 15458,
       "failureRate": 0.9423,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 925,
       "successCount": 946,
       "successRate": 0.0577,
-      "total": 16403,
+      "total": 16404,
-      "unresolvedFailureCount": 8614
+      "unresolvedFailureCount": 8615
     },
     "warnings": [
       "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
       "组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -38044,6 +38068,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 16597,
+  "summarizedRecords": 16598,
   "version": 1
 }

manifest.json

@@ -2,24 +2,24 @@
   "agentVersion": "2026.09.20.2",
   "checksums": {
     ".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f",
-    ".modelhub_state/architecture_compatibility_blacklist.json": "1489bde9cd932323e0346b247b137c26f993957c2e2fb0f01d85a3934991e06b",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "c95d68825ceb1b7ea42f076f269a263c541dbe1efbd30a11dbfce0cb62158082",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
     ".modelhub_state/market_intelligence.json": "126f0f93bb036192a1f2caffe85b600f910c4aa4f3dd87370d6286267ac00a1c",
     ".modelhub_state/official_capabilities.json": "61c269162ac96a9233f25fde465c87fcc14005200a4e6b7bcbf866f8b963fb4e",
-    ".modelhub_state/outcome_checkpoint.json": "0e41e62390af82dec938795049dbfea5a0033d3d82f74dd91603f1aae71c69f1",
+    ".modelhub_state/outcome_checkpoint.json": "44bc8c9ee35363d0ad41d5733758d0fc0d4188075deedc067970ef2257ab505e",
     ".modelhub_state/queue_cleanup_latest.json": "f93bde2de8f7cc7073f34b5456a3df43c8f54023eacfce210dc11e227efd469c",
     ".modelhub_state/recent_outcomes.jsonl": "9e2a4dc46246785df8dffcbd4b6aea5cc0b32794af784e60d3a212af041c91c6",
-    ".modelhub_state/recovery_active_tasks.jsonl": "dac96352e408bb91ec1013f7838f75643645ba626a687a594cecceafed4229d4",
+    ".modelhub_state/recovery_active_tasks.jsonl": "edd0e779b6734e05bbb8b2c9c7a57e05b8913584b263248467ce2133c3f821c0",
-    ".modelhub_state/recovery_intents.jsonl": "d82c8aaa2ded6636d6ba732cbea686fad3773d8e3d5a5ed0eae6c153ff65c361",
+    ".modelhub_state/recovery_intents.jsonl": "d236f73446599d5b69f8a517dd97be16ffb3ccf8baba830b19257f1b54ce832d",
     ".modelhub_state/routing_intelligence.json": "2cd79876e6a12531ba2735385756a6e9500176eb79d0a50ff9084bde74a581f2",
     ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
     ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
     "ledger/submissions.jsonl": "c3f26b5e027107d42662509dd24d6b293b5ce9acd38a0a9e3c525b7bf7bf354d",
-    "outcomes/submissions.jsonl": "e82c8291b9f6b7c74e672343d91da5b01ec595fbbbcf597937ccadcff4bbf4ae"
+    "outcomes/submissions.jsonl": "a44b1d20f0dbfd2788ef03d385da58b8f27d5d471e33fdfa3f1905afd2fe1ee2"
   },
-  "generation": 11713,
+  "generation": 11714,
-  "phase": "cycle",
+  "phase": "cycle_no_slots",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-21T20:29:05.180722+00:00",
+  "updatedAt": "2026-09-21T20:30:04.257841+00:00",
   "writerId": "8b35139af6674067a339a670222d4b67"
 }

outcomes/submissions.jsonl

@@ -417,7 +417,6 @@
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:30:54.600004+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:24:23.579461+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969573", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600433+00:00", "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221588}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:24:23.586939+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969576", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600240+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663410366, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663410366}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:24:23.730955+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969577", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600371+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663591}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:24:23.751982+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969579", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600185+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.241562+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969620", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600422+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:31.903313+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969626", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.599992+00:00", "modelId": "RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325064, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325064}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.042085+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969633", "taskType": "text-generation", "verifyResult": null}