state: generation 5161 (cycle)

This commit is contained in:
2026-09-10 12:34:08 +00:00
parent 9f9687d4a8
commit 9b5d15353f
9 changed files with 2007 additions and 2008 deletions

View File

@@ -1313,7 +1313,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T12:31:29.194861+00:00",
"generatedAt": "2026-09-10T12:34:07.518440+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -11,7 +11,7 @@
"1": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 367,
"listingErrors": 368,
"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": "2026-09-10T12:31:29.170994+00:00",
"updatedAt": "2026-09-10T12:34:07.494969+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T12:29:21.493262+00:00",
"generatedAt": "2026-09-10T12:32:36.760432+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": "2026-09-10T12:23:25.924304+00:00",
"lastSyncTime": "2026-09-10T12:23:25.501745+00:00",
"generatedAt": "2026-09-10T12:32:30.185165+00:00",
"lastSyncTime": "2026-09-10T12:32:29.847014+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2145,12 +2145,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 55,
"ambiguous_runtime": 56,
"framework_architecture_unsupported": 38,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 99,
"failureCount": 100,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2160,8 +2160,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 99,
"unresolvedFailureCount": 55
"total": 100,
"unresolvedFailureCount": 56
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -2323,7 +2323,7 @@
"decisionSuccessRate": 0.0042,
"decisionTotal": 237,
"failureBreakdown": {
"ambiguous_runtime": 171,
"ambiguous_runtime": 172,
"backend_operator": 29,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2334,15 +2334,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 432,
"failureCount": 433,
"failureRate": 0.9977,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0023,
"total": 433,
"unresolvedFailureCount": 195
"total": 434,
"unresolvedFailureCount": 196
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2445,7 +2445,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T12:23:25.917637+00:00",
"generatedAt": "2026-09-10T12:32:30.179883+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2730,22 +2730,22 @@
"decisionSuccessRate": 0.2167,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 56,
"ambiguous_runtime": 57,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 246,
"failureRate": 0.9498,
"failureCount": 247,
"failureRate": 0.95,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0502,
"total": 259,
"unresolvedFailureCount": 199
"successRate": 0.05,
"total": 260,
"unresolvedFailureCount": 200
},
"hygon_k100-ai": {
"attributableFailureCount": 39,
@@ -4545,7 +4545,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T12:23:25.501701+00:00",
"lastTerminalAt": "2026-09-10T12:32:29.847014+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7031,15 +7031,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1583,
"totalRecords": 1670,
"terminalRecords": 1584,
"totalRecords": 1671,
"totals": {
"attributableFailureCount": 414,
"decisionFailureRate": 0.8903,
"decisionSuccessRate": 0.1097,
"decisionTotal": 465,
"failureBreakdown": {
"ambiguous_runtime": 344,
"ambiguous_runtime": 345,
"backend_operator": 35,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
@@ -7051,21 +7051,21 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1532,
"failureCount": 1533,
"failureRate": 0.9678,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 51,
"successRate": 0.0322,
"total": 1583,
"unresolvedFailureCount": 1115
"total": 1584,
"unresolvedFailureCount": 1116
},
"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。",
@@ -7073,7 +7073,7 @@
"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。",
@@ -7094,6 +7094,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1670,
"summarizedRecords": 1671,
"version": 1
}

View File

@@ -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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T12:32:29.847014+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:27:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477841", "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": "2026-09-10T12:23:25.501701+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:23:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471971", "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": "2026-09-10T12:23:25.501713+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:19:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471969", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-10T12:23:25.501677+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493612", "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": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T00:41:43.539049+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T00:35:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4481795", "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": "2026-09-08T00:32:26.904386+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T00:29:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4481796", "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, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-08T00:22:46.993284+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T00:13:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4482440", "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": "2026-09-07T23:53:16.902664+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:51:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4479115", "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": "61d4ceb4c076672f67574ef859ef4d0a39d9db0193a80b2bb12cae84cebf427a",
".modelhub_state/architecture_history_backfill.json": "db12b1ea7346c8d8f1f3244571823942c9c26653df6dfedb859b65934d1d8827",
".modelhub_state/market_intelligence.json": "eecc929d0cfa3f6c9ca18cfbea4ccdd0b2c01e9df932b43acfd584f935fea9c5",
".modelhub_state/official_capabilities.json": "ee23fb3f47e194a953bf872b7736661a194f1dc3ad06d2575f44aaba745d3a06",
".modelhub_state/outcome_checkpoint.json": "e2d6d4e2e03343baface59172753e2107d9b1071c1edee6515e5cb8d0ee16554",
".modelhub_state/architecture_compatibility_blacklist.json": "0add83c00bc771d879050e003284b9a73b966eb5745d7cb188b952fdf884b8bd",
".modelhub_state/architecture_history_backfill.json": "6e6a6e74ddd49bee67dc6aa9b8bcc9b8540112eb149dfff7b230f4e97ebe86ed",
".modelhub_state/market_intelligence.json": "6aaf73bac91d48a0c64a67bd6b726c331f2447350b22a41bb841344c603f2790",
".modelhub_state/official_capabilities.json": "54f0e2e7426c5851425cbc33397f2e024bb12aee2e09e1561e42df94413268a9",
".modelhub_state/outcome_checkpoint.json": "11adf97f277d22140193a2f9796e1217be2f6b9d5ae09527cb769bea9d9c9489",
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
".modelhub_state/recent_outcomes.jsonl": "5c42a62e2f1eb6eba9a917b8a42a911fe987bb994ca97d17c1f26f91f106ae09",
".modelhub_state/recovery_active_tasks.jsonl": "d043fadc304d6c14a059ba4ea366d86d43b04ccad91f0e7f7df05e40157f9a82",
".modelhub_state/recovery_intents.jsonl": "d5b10c98f11d1259d12e879a563560a7c1bbdb454505e4deac13cfd934572884",
".modelhub_state/recent_outcomes.jsonl": "46859aa57c7e6a38cf09bc7d4b199b76cdd8427bf6be340d93303deb2e1a83a3",
".modelhub_state/recovery_active_tasks.jsonl": "0c5cf3113245d143c00114624a023745c9718bf8b3dc19ee01500bfe3434f613",
".modelhub_state/recovery_intents.jsonl": "c6c1e6a5e633bcc9a5e51994d56e0435c85fc2579a5ddf3da63d96e36d2692b2",
".modelhub_state/routing_intelligence.json": "f36cfaf9f9ff191164b0ce0a73a3ce4bbc3a2dc4589f252d583e33b427807fc0",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "8a621da5637d481c7de4b4e3375f2a68cbdabf71fe459244a727034f36ab3eb9",
"outcomes/submissions.jsonl": "249bd947bbece33d1e7d20b546c76ca577966a52b7f8d45fcbf882be0353517a"
},
"generation": 5160,
"generation": 5161,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T12:31:29.258968+00:00",
"updatedAt": "2026-09-10T12:34:08.273657+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}