state: generation 5390 (cycle)

This commit is contained in:
2026-09-10 22:41:05 +00:00
parent 953f88eb24
commit 922e8e1e4b
9 changed files with 2026 additions and 2026 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T22:38:21.159273+00:00",
"generatedAt": "2026-09-10T22:41:05.242957+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 383,
"listingErrors": 384,
"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": 11,
"nextAccountIndex": 0,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T22:38:21.135641+00:00",
"updatedAt": "2026-09-10T22:41:05.217239+00:00",
"version": 1
}

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-10T22:23:26.029527+00:00",
"communityAttemptedAt": "2026-09-10T22:39:29.283603+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-10T22:23:26.029527+00:00",
"communityUpdatedAt": "2026-09-10T22:39:29.283603+00:00",
"frameworkAttemptedAt": "2026-09-10T21:27:33.050021+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T22:36:54.422203+00:00",
"generatedAt": "2026-09-10T22:39:29.283603+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": "2026-09-10T22:32:18.653428+00:00",
"lastSyncTime": "2026-09-10T22:32:18.404549+00:00",
"generatedAt": "2026-09-10T22:39:22.030091+00:00",
"lastSyncTime": "2026-09-10T22:39:21.821546+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1997,7 +1997,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 39,
"ambiguous_runtime": 40,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
@@ -2006,7 +2006,7 @@
"runtime_memory": 2,
"参数/模板问题": 3
},
"failureCount": 74,
"failureCount": 75,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2016,8 +2016,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 74,
"unresolvedFailureCount": 42
"total": 75,
"unresolvedFailureCount": 43
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2319,7 +2319,7 @@
"decisionSuccessRate": 0.0123,
"decisionTotal": 243,
"failureBreakdown": {
"ambiguous_runtime": 191,
"ambiguous_runtime": 192,
"backend_operator": 33,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2330,15 +2330,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 456,
"failureCount": 457,
"failureRate": 0.9935,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0065,
"total": 459,
"unresolvedFailureCount": 215
"total": 460,
"unresolvedFailureCount": 216
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2441,7 +2441,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T22:32:18.648665+00:00",
"generatedAt": "2026-09-10T22:39:22.025914+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2678,7 +2678,7 @@
"decisionSuccessRate": 0.0571,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 39,
"ambiguous_runtime": 40,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
@@ -2688,15 +2688,15 @@
"参数/模板问题": 10,
"验证失败": 26
},
"failureCount": 108,
"failureRate": 0.9818,
"failureCount": 109,
"failureRate": 0.982,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0182,
"total": 110,
"unresolvedFailureCount": 75
"successRate": 0.018,
"total": 111,
"unresolvedFailureCount": 76
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 36,
@@ -4192,9 +4192,9 @@
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"参数/模板问题": 9
"参数/模板问题": 8
},
"failureCount": 11,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4206,8 +4206,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 11,
"unresolvedFailureCount": 9
"total": 10,
"unresolvedFailureCount": 8
},
"Iluvatar_bi-100|transformers|text-generation": {
"attributableFailureCount": 0,
@@ -4406,7 +4406,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T22:32:18.404515+00:00",
"lastTerminalAt": "2026-09-10T22:39:21.821546+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -6988,15 +6988,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1637,
"totalRecords": 1724,
"terminalRecords": 1638,
"totalRecords": 1725,
"totals": {
"attributableFailureCount": 426,
"decisionFailureRate": 0.8894,
"decisionSuccessRate": 0.1106,
"decisionTotal": 479,
"failureBreakdown": {
"ambiguous_runtime": 383,
"ambiguous_runtime": 384,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
@@ -7008,30 +7008,31 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1584,
"failureCount": 1585,
"failureRate": 0.9676,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.0324,
"total": 1637,
"unresolvedFailureCount": 1154
"total": 1638,
"unresolvedFailureCount": 1155
},
"warnings": [
"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 Iluvatar_mrv-100 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 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 MetaX_c-500 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 Biren_166m 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 Iluvatar_bi-150 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 Cambricon_mlu-370-x8 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 Ascend_910-b4 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-x4|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 Mthreads_s4000|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 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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7046,11 +7047,10 @@
"组合 hygon_k100-ai|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 Iluvatar_bi-150|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 Vastai_va16|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 Cambricon_mlu-370-x4|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 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1724,
"summarizedRecords": 1725,
"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": "2026-09-10T22:39:21.821546+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T22:33:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532025", "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": "2026-09-10T22:32:18.404515+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T22:25:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4583642", "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": "2026-09-10T21:23:30.606595+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T21:17:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532126", "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": "2026-09-10T21:23:30.606628+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T21:17:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532125", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831391+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.797429+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712830", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831425+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.795480+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712823", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831439+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.791128+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712828", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831489+00:00", "modelId": "empero-ai/Qwen3.8-9B-Distill", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.788912+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712827", "taskType": "text-generation", "verifyResult": null}

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": "922be21281775fad24112e330a8bd7d31acbb7958c93d5a0fa09485735ebe58d",
".modelhub_state/architecture_history_backfill.json": "014616ff69a52bdefce62847c910c6a4a108100a4496cbbc202890035924a12e",
".modelhub_state/market_intelligence.json": "a6ee2d7b044a3f61ea2dc6183d0fa3cb82de7358178eee8cebb9845dba5ed8c9",
".modelhub_state/official_capabilities.json": "7f40c3abc4d53b9c5e68f301f9819cf98ab080f7a70b4357cad71c130ed2dfdf",
".modelhub_state/outcome_checkpoint.json": "7291992051a6b31e6f314bc83b7e7c4925d7e394c8427a213cda202129f2a534",
".modelhub_state/architecture_compatibility_blacklist.json": "191699d3f93dfbfb1264d8c58c8982c041f306299ef37132b0cdc3e627af853d",
".modelhub_state/architecture_history_backfill.json": "86faaf1937f3c3f7972a4f1128d495f102616baf3ae3f3f1d8aea2f4f61f7a4f",
".modelhub_state/market_intelligence.json": "005df1c9c4daf3de4bf035d8753fd900e4f5d19ba1b4f0e834a9aca2f00e93f9",
".modelhub_state/official_capabilities.json": "509f436a2ac8ec98e5cd88b3d8cff9c3ea9e65427dc45aa86ae10ba53deeb183",
".modelhub_state/outcome_checkpoint.json": "f9e205f02e05a8a14a8d27fd8f0fe2628758dd4425980a543c65ca57136d41cf",
".modelhub_state/queue_cleanup_latest.json": "777f4bec9250957bd6a5571440bc1d401209444f7c4aa372f2de9033886894e5",
".modelhub_state/recent_outcomes.jsonl": "c7cd466b61d5d2f434c6384a9e5cdcdc0dff122fa79711c7a9a1d0ef9c70c30f",
".modelhub_state/recovery_active_tasks.jsonl": "689018182118dee9bcdf5a70a3f26f04ec8abb5f88e7493fb512b05f818bf518",
".modelhub_state/recovery_intents.jsonl": "5440d1407c15a785d29cd1b6da820362e5668a0bf7299f93232e2c3a551719ca",
".modelhub_state/recent_outcomes.jsonl": "fdb4c0dc058871c9d9f13be6a30a06347677fdc2e4bcc1902d9f9d0fbc63279c",
".modelhub_state/recovery_active_tasks.jsonl": "373b7a847e075ab409be28cab1c0c5d602e575d5fb227a336fe56bf1771efab6",
".modelhub_state/recovery_intents.jsonl": "32b1c9799d6126fb4832a390bdcf85967f0dee4d8b9b62a0817c1701084227cd",
".modelhub_state/routing_intelligence.json": "e3d23a5e6afd96c3481aa525fd641500a5693cc776defa488e9749eeeca78057",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "70b6cae0b58ec41be21dadaa435c9a39a06725619fd8619bf24a2aeafa24a8dc",
"outcomes/submissions.jsonl": "09d80f611694cdc2f5e1e4a4a0ddb207de6ea8e6638cfd2da5eb051e8397a6e1"
},
"generation": 5389,
"generation": 5390,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T22:38:21.239288+00:00",
"updatedAt": "2026-09-10T22:41:05.784864+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}