state: generation 4999 (cycle)

This commit is contained in:
2026-09-10 06:05:16 +00:00
parent a4ceda8684
commit f94fead963
9 changed files with 2105 additions and 2107 deletions

View File

@@ -1323,7 +1323,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T06:03:44.849557+00:00",
"generatedAt": "2026-09-10T06:05:15.656336+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -75,7 +75,7 @@
"7": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 355,
"listingErrors": 356,
"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": "2026-09-10T06:03:44.819548+00:00",
"updatedAt": "2026-09-10T06:05:15.626941+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T06:01:39.033026+00:00",
"generatedAt": "2026-09-10T06:03:48.414016+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T05:56:10.537740+00:00",
"lastSyncTime": "2026-09-10T05:56:10.303668+00:00",
"generatedAt": "2026-09-10T06:03:48.379702+00:00",
"lastSyncTime": "2026-09-10T06:03:48.106939+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2153,12 +2153,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 48,
"ambiguous_runtime": 49,
"framework_architecture_unsupported": 38,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 92,
"failureCount": 93,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2168,8 +2168,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 92,
"unresolvedFailureCount": 48
"total": 93,
"unresolvedFailureCount": 49
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -2241,14 +2241,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 1
},
"failureCount": 45,
"failureCount": 46,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2258,8 +2258,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 45,
"unresolvedFailureCount": 10
"total": 46,
"unresolvedFailureCount": 11
}
},
"frameworkSummaries": {
@@ -2331,7 +2331,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 230,
"failureBreakdown": {
"ambiguous_runtime": 141,
"ambiguous_runtime": 143,
"backend_operator": 24,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2342,15 +2342,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 393,
"failureCount": 395,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 393,
"unresolvedFailureCount": 162
"total": 395,
"unresolvedFailureCount": 164
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2453,7 +2453,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T05:56:10.533885+00:00",
"generatedAt": "2026-09-10T06:03:48.375637+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2737,22 +2737,22 @@
"decisionSuccessRate": 0.2167,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 49,
"ambiguous_runtime": 50,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 239,
"failureRate": 0.9484,
"failureCount": 240,
"failureRate": 0.9486,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0516,
"total": 252,
"unresolvedFailureCount": 192
"successRate": 0.0514,
"total": 253,
"unresolvedFailureCount": 193
},
"hygon_k100-ai": {
"attributableFailureCount": 38,
@@ -2760,7 +2760,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 12,
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"model_load": 3,
@@ -2769,15 +2769,15 @@
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 85,
"failureCount": 86,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 85,
"unresolvedFailureCount": 47
"total": 86,
"unresolvedFailureCount": 48
}
},
"observedGpuMemoryGiB": {
@@ -4569,21 +4569,21 @@
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 4
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 3
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T05:56:10.303668+00:00",
"lastTerminalAt": "2026-09-10T06:03:48.106911+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4592,7 +4592,7 @@
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 16
"unresolvedFailureCount": 17
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -4652,16 +4652,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 9,
"framework_architecture_unsupported": 8,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 18,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T04:54:16.213427+00:00",
"lastTerminalAt": "2026-09-10T06:03:48.106939+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4669,8 +4669,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 18,
"unresolvedFailureCount": 8
"total": 19,
"unresolvedFailureCount": 9
}
},
"recentProfileCombinationStats": {
@@ -6879,15 +6879,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1511,
"totalRecords": 1598,
"terminalRecords": 1513,
"totalRecords": 1600,
"totals": {
"attributableFailureCount": 400,
"decisionFailureRate": 0.8909,
"decisionSuccessRate": 0.1091,
"decisionTotal": 449,
"failureBreakdown": {
"ambiguous_runtime": 292,
"ambiguous_runtime": 294,
"backend_operator": 29,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -6899,21 +6899,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1462,
"failureCount": 1464,
"failureRate": 0.9676,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0324,
"total": 1511,
"unresolvedFailureCount": 1060
"total": 1513,
"unresolvedFailureCount": 1062
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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 Iluvatar_mrv-100 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 Sunrise_pt-200-x1 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 Vastai_va16 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。",
@@ -6921,7 +6921,7 @@
"GPU hygon_k100-ai 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 Mthreads_s4000 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 Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_mrv-100|unknown|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|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -6942,6 +6942,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1598,
"summarizedRecords": 1600,
"version": 1
}

View File

@@ -1,3 +1,5 @@
{"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": "2026-09-10T06:03:48.106911+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:59:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471974", "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": "2026-09-10T06:03:48.106939+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:57:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493605", "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": "2026-09-10T05:56:10.303668+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:55:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477782", "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": "2026-09-10T05:49:48.500487+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:45:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471903", "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": "2026-09-10T05:49:48.500463+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:43:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471905", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +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_moe"], "framework": "vllm", "lastSyncTime": "2026-09-07T11:33:34.194572+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T11:29:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4460293", "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": "2026-09-07T11:33:34.194583+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T11:27:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4460584", "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": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-07T11:33:34.194592+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T11:19:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4421469", "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": ["LlavaLlamaForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-07T11:12:18.209215+00:00", "modelId": "microsoft/llava-med-7b-delta", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T11:03:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079287", "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": ["Phi4FlashForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-07T11:12:18.209201+00:00", "modelId": "microsoft/Phi-4-mini-flash-reasoning", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:57:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079234", "taskType": "text-generation", "verifyResult": -1}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "441cf88b3c594d280498fbba73936226e5af95ffca9c5e7a53028a9759bdf219",
".modelhub_state/architecture_history_backfill.json": "495d07e8dfc26eb634b670f407fcb33da69426bb3d2760c0e756b31d34ad1ebd",
".modelhub_state/market_intelligence.json": "7a1a9f19c6d1ba050bcc8ca3fed6d8775b64533478451a44329fe07a8a169d6d",
".modelhub_state/official_capabilities.json": "9ce4b6040602df993d1a1c50bcb0922050ba85389cb78a5680c7f6632e9bb56c",
".modelhub_state/outcome_checkpoint.json": "d3c796360452c81fea3db2b995a2e745a03dfccf3b9d0c7fada3194ac234a341",
".modelhub_state/architecture_compatibility_blacklist.json": "72bd6a2b7d991530c0237ce428bf9154cf5febb053b952eec02ce673cd0ba02e",
".modelhub_state/architecture_history_backfill.json": "4ff1df2a50a99517a98a523a444fa71609e575ba7cfb6b7e1bae7ebf3713e614",
".modelhub_state/market_intelligence.json": "bf9fb05188fdb10827a514c5523c73535d552ae6e107a4043f89d71d828959e6",
".modelhub_state/official_capabilities.json": "632242e68d015781bc46bde76dced69795bf7fa23979007e1f2b5ad7043ffa91",
".modelhub_state/outcome_checkpoint.json": "b3d1c266ca02420bfe9fd51a998acfb646d2d55c1fc20b5fba32ebb44f4050ee",
".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99",
".modelhub_state/recent_outcomes.jsonl": "2de4abdb11aac7494df688e37d611995b5daa15ca3d778b109947bb2c6a3e78c",
".modelhub_state/recovery_active_tasks.jsonl": "1acd03a5bd0611bb0b67595f7f49f564c7ff82d75b9f0325cf339e615ae7600e",
".modelhub_state/recovery_intents.jsonl": "b2d2fefa740064fbbf03998ad630149740d204913a3c8e6a365b340bc64df264",
".modelhub_state/recent_outcomes.jsonl": "fe315011c870521f867a99cbaeb13ed5c634883c5f8fd597757b84e80cdc77b4",
".modelhub_state/recovery_active_tasks.jsonl": "98d6085d5cea77e8fe6a9884fb587dc72a819d709c4552bcc9a76ea2e8b162a8",
".modelhub_state/recovery_intents.jsonl": "b75661b70d54583c345a8853873dae6470372c5619f086f61a9eb7e432211d16",
".modelhub_state/routing_intelligence.json": "f9ebf6b7b8ae06030c651e7942b7a357d8a2828edad8391c2935e2c435fcf497",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "f8c7284660af100fbfd1e800575e7f1036b4a56ca15236b7f07bff4420937641",
"outcomes/submissions.jsonl": "6cdac6e896b7a46d7840479a2688ba41eb22b6cee6da70c8283458e179ac94f8"
},
"generation": 4998,
"generation": 4999,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T06:03:45.373003+00:00",
"updatedAt": "2026-09-10T06:05:16.427963+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}