state: generation 5146 (cycle)

This commit is contained in:
2026-09-10 11:50:56 +00:00
parent e29a34e597
commit 2870a0c75a
9 changed files with 2009 additions and 2012 deletions

View File

@@ -1313,7 +1313,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T11:47:56.563701+00:00",
"generatedAt": "2026-09-10T11:50:55.607167+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -19,7 +19,7 @@
"10": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 365,
"listingErrors": 366,
"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": 10,
"nextAccountIndex": 11,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T11:47:56.538340+00:00",
"updatedAt": "2026-09-10T11:50:55.584586+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T11:46:22.953096+00:00",
"generatedAt": "2026-09-10T11:49:06.765404+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": "2026-09-10T11:40:52.921299+00:00",
"lastSyncTime": "2026-09-10T11:40:52.603367+00:00",
"generatedAt": "2026-09-10T11:48:58.707806+00:00",
"lastSyncTime": "2026-09-10T11:48:57.307255+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2046,17 +2046,17 @@
"unresolvedFailureCount": 33
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 33,
"attributableFailureCount": 34,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 33,
"decisionTotal": 34,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"platform_infrastructure": 2,
"tokenizer_compatibility": 31,
"tokenizer_compatibility": 32,
"参数/模板问题": 6
},
"failureCount": 41,
"failureCount": 42,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2066,7 +2066,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 41,
"total": 42,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -2402,26 +2402,26 @@
"unresolvedFailureCount": 4
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 36,
"attributableFailureCount": 37,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 36,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 29,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 31,
"tokenizer_compatibility": 32,
"参数/模板问题": 7
},
"failureCount": 74,
"failureCount": 75,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 74,
"total": 75,
"unresolvedFailureCount": 36
},
"vllm_tokenizer_patch": {
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T11:40:52.916454+00:00",
"generatedAt": "2026-09-10T11:48:58.703511+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2700,25 +2700,25 @@
"unresolvedFailureCount": 60
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 34,
"decisionFailureRate": 0.9714,
"decisionSuccessRate": 0.0286,
"decisionTotal": 35,
"attributableFailureCount": 35,
"decisionFailureRate": 0.9722,
"decisionSuccessRate": 0.0278,
"decisionTotal": 36,
"failureBreakdown": {
"framework_architecture_unsupported": 3,
"platform_infrastructure": 3,
"tokenizer_compatibility": 31,
"tokenizer_compatibility": 32,
"参数/模板问题": 9,
"验证失败": 32
},
"failureCount": 78,
"failureRate": 0.9873,
"failureCount": 79,
"failureRate": 0.9875,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 1,
"successRate": 0.0127,
"total": 79,
"successRate": 0.0125,
"total": 80,
"unresolvedFailureCount": 41
},
"Vastai_va16": {
@@ -4451,22 +4451,22 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 12,
"consecutiveFailures": 12,
"attributableFailureCount": 13,
"consecutiveFailures": 13,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 12,
"decisionTotal": 13,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 11
"tokenizer_compatibility": 12
},
"failureCount": 14,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-10T11:01:21+00:00",
"lastTerminalAt": "2026-09-10T11:14:50.402520+00:00",
"lastTerminalAt": "2026-09-10T11:48:57.307255+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
@@ -4474,7 +4474,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 14,
"total": 15,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -7002,13 +7002,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1568,
"totalRecords": 1655,
"terminalRecords": 1569,
"totalRecords": 1656,
"totals": {
"attributableFailureCount": 409,
"decisionFailureRate": 0.8891,
"decisionSuccessRate": 0.1109,
"decisionTotal": 460,
"attributableFailureCount": 410,
"decisionFailureRate": 0.8894,
"decisionSuccessRate": 0.1106,
"decisionTotal": 461,
"failureBreakdown": {
"ambiguous_runtime": 337,
"backend_operator": 34,
@@ -7018,25 +7018,25 @@
"platform_infrastructure": 3,
"repository_structure": 5,
"runtime_memory": 5,
"tokenizer_compatibility": 37,
"tokenizer_compatibility": 38,
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1517,
"failureCount": 1518,
"failureRate": 0.9675,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 51,
"successRate": 0.0325,
"total": 1568,
"total": 1569,
"unresolvedFailureCount": 1105
},
"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 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。",
"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。",
@@ -7044,7 +7044,7 @@
"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 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。",
"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。",
@@ -7065,6 +7065,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1655,
"summarizedRecords": 1656,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T11:48:57.307255+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:45:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458000", "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": "2026-09-10T11:40:52.603333+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:39:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505113", "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": "2026-09-10T11:40:52.603356+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:39:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505112", "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": "2026-09-10T11:40:52.603367+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:37:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505111", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-07T23:25:25.308759+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:21:22+00:00", "targetGpu": "Biren_166m", "taskId": "4610397", "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": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-07T23:25:25.308783+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:19:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4133677", "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": "2026-09-07T23:16:42.601369+00:00", "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:15:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332994", "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": "2026-09-07T23:16:42.601390+00:00", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4083483", "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": "181e6e67d49e8914d13eb152c9f80cc9804eec092897242463872a2a5276eff9",
".modelhub_state/architecture_history_backfill.json": "da5b5d5b0b76751fb3deb325bb9b4e98ece83acbb80668c2b6e3d5095cb9162c",
".modelhub_state/market_intelligence.json": "4eae871d5db415d28cb22dade54b684a719d2c3cbf90fbd4f79fe0e37d570263",
".modelhub_state/official_capabilities.json": "151fdb5a88acc3c17106a78449e6d04a6a85f7e65c2804d367167f5c231d7a84",
".modelhub_state/outcome_checkpoint.json": "3f40fbd199c8837295f6115a33da6d87af6e23d76c4b7d3949f8aba7c0067e82",
".modelhub_state/architecture_compatibility_blacklist.json": "44441830c0c7c5f306dfdf530da3bac12dff8e15f8820f445d5f31745fd0fdd5",
".modelhub_state/architecture_history_backfill.json": "4c5383a893c0ce774f7e7b66728471129117f20c36e08fa2a49107300e7e1e63",
".modelhub_state/market_intelligence.json": "e177006f40c675b6483e07697c33f6062b4df6d475ce9b4f746fb733b52e1a7b",
".modelhub_state/official_capabilities.json": "6aa4c2ad45d0ba5fb4dc3685231b12963276ceefe650f9776ad63f7d9750b6ce",
".modelhub_state/outcome_checkpoint.json": "9daec34241f100bae109cbb8b42a81d33e2cdb9d34003a22ede09d6ebf3f748b",
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
".modelhub_state/recent_outcomes.jsonl": "9c76c675711d73c096bf81946bd4da6c45a966e8714578e5904f9f8e3e999694",
".modelhub_state/recovery_active_tasks.jsonl": "f943a1254b5aa8966d0fcd18531de3065c2e6d3bc53afca50621a9320726e14f",
".modelhub_state/recovery_intents.jsonl": "549bd73ef02af451a46894496547fc2c1bbd90b6329feef562a80fdc5c75e5b5",
".modelhub_state/recent_outcomes.jsonl": "c3d77c45157ba5a636046acfd882e9e6fe6fe8e1d4d35d8d3e918a3eee5dbe19",
".modelhub_state/recovery_active_tasks.jsonl": "1545f4272e067683af163cef9424856474281f6aa28b9038e8d54f99d8a94526",
".modelhub_state/recovery_intents.jsonl": "316d42b4b95c5a86c413263c2855712a859743c27c4856cec89a24a401319423",
".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": "eaa6922265ab874d46282c8353419da53665ddca2baca53c5b4240e410666d50"
},
"generation": 5145,
"generation": 5146,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T11:47:56.661402+00:00",
"updatedAt": "2026-09-10T11:50:56.237951+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}