state: generation 5541 (cycle)

This commit is contained in:
2026-09-11 05:09:56 +00:00
parent c2cd83f5ce
commit 4f82defa8d
9 changed files with 2039 additions and 2040 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-11T05:06:59.369407+00:00",
"generatedAt": "2026-09-11T05:09:55.446809+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -83,7 +83,7 @@
"8": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 395,
"listingErrors": 396,
"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": 8,
"nextAccountIndex": 9,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-11T05:06:59.336204+00:00",
"updatedAt": "2026-09-11T05:09:55.423468+00:00",
"version": 1
}

View File

@@ -387,7 +387,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T05:05:02.392111+00:00",
"generatedAt": "2026-09-11T05:08:06.138989+00:00",
"gpuStats": {
"Ascend_910-b4": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-11T03:33:49.103183+00:00",
"lastSyncTime": "2026-09-11T03:33:48.898214+00:00",
"generatedAt": "2026-09-11T05:08:00.294271+00:00",
"lastSyncTime": "2026-09-11T05:08:00.009961+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2140,12 +2140,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 60,
"ambiguous_runtime": 61,
"framework_architecture_unsupported": 38,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 104,
"failureCount": 105,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2155,8 +2155,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 104,
"unresolvedFailureCount": 60
"total": 105,
"unresolvedFailureCount": 61
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -2319,7 +2319,7 @@
"decisionSuccessRate": 0.0123,
"decisionTotal": 243,
"failureBreakdown": {
"ambiguous_runtime": 194,
"ambiguous_runtime": 195,
"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": 459,
"failureCount": 460,
"failureRate": 0.9935,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0065,
"total": 462,
"unresolvedFailureCount": 218
"total": 463,
"unresolvedFailureCount": 219
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2441,7 +2441,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T03:33:49.099427+00:00",
"generatedAt": "2026-09-11T05:08:00.290509+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2727,22 +2727,22 @@
"decisionSuccessRate": 0.2167,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 62,
"ambiguous_runtime": 63,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 252,
"failureRate": 0.9509,
"failureCount": 253,
"failureRate": 0.9511,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0491,
"total": 265,
"unresolvedFailureCount": 205
"successRate": 0.0489,
"total": 266,
"unresolvedFailureCount": 206
},
"hygon_k100-ai": {
"attributableFailureCount": 39,
@@ -4190,9 +4190,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 3
"参数/模板问题": 2
},
"failureCount": 3,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4204,8 +4204,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-100|transformers|text-generation": {
"attributableFailureCount": 0,
@@ -4531,7 +4531,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T23:52:39.100972+00:00",
"lastTerminalAt": "2026-09-11T05:08:00.009961+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -6936,15 +6936,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1645,
"totalRecords": 1732,
"terminalRecords": 1646,
"totalRecords": 1733,
"totals": {
"attributableFailureCount": 427,
"decisionFailureRate": 0.8896,
"decisionSuccessRate": 0.1104,
"decisionTotal": 480,
"failureBreakdown": {
"ambiguous_runtime": 390,
"ambiguous_runtime": 391,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
@@ -6956,31 +6956,30 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1592,
"failureCount": 1593,
"failureRate": 0.9678,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.0322,
"total": 1645,
"unresolvedFailureCount": 1161
"total": 1646,
"unresolvedFailureCount": 1162
},
"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 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。",
"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 Cambricon_mlu-370-x4 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。",
@@ -6995,10 +6994,11 @@
"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": 1732,
"summarizedRecords": 1733,
"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": "2026-09-11T05:08:00.009961+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T05:05:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477832", "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": "2026-09-11T03:33:48.898214+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T03:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497066", "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": "2026-09-11T03:25:05.807699+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T03:23:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497054", "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, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T23:52:39.100972+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T23:51:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477786", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T07:22:29.130684+00:00", "modelId": "nightmedia/Mistral-Nemo-Instruct-2407-12B-Thinking-M-Claude-Opus-High-Reasoning-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:19:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079225", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831495+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.934706+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712836", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831446+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.928754+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712837", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831476+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.927161+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712835", "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": "f2e724f16f76b1708552affe9b08f38901cb80593670db4fe4119b06fc27fa76",
".modelhub_state/architecture_history_backfill.json": "e303bc6aa29a44edde865aa03e3907ba229db326ef44d9d12f28e6f4e16fdee6",
".modelhub_state/market_intelligence.json": "c404e7a83f5480ea5a7b71a58d0bba3762525ff2d2202b076d78835105ac853c",
".modelhub_state/official_capabilities.json": "dcf0050e01ac843f19791fa2ee4728c3e42806fbecca7f4bd06226fe5c05b9e1",
".modelhub_state/outcome_checkpoint.json": "f79b0cf8c8d78cb276a7074d4430aa3bb8d5a6e9e047a99be83b7839affea55d",
".modelhub_state/architecture_compatibility_blacklist.json": "221e51bfc5346faa433c1aec4f9fc88bdd493abe0fc2e97a907a4eb766a76eba",
".modelhub_state/architecture_history_backfill.json": "522ec3dacde1a603fc0acbcc29979f58dee8bd9670952f3ff1d59de944d7d161",
".modelhub_state/market_intelligence.json": "520fcd6dbff0cfdf7bec69bdc22837df35c44a516c93ea909c9a7ea649361f75",
".modelhub_state/official_capabilities.json": "f55935cad05713f5b211cd6e6004b4247da38eb98d6560c068a5ee5da6492b97",
".modelhub_state/outcome_checkpoint.json": "59f7925f7bc93a51dafff6540fd40899e0cd19560b646bc83bb5d2cb2c782be9",
".modelhub_state/queue_cleanup_latest.json": "757bb52cd4c1e398d565b25c01e1a394e97727dc87500e4184be2784f229ae2a",
".modelhub_state/recent_outcomes.jsonl": "cd38593344e217489915142ed481535713d3230c773d364e965c12e8bf6e84a9",
".modelhub_state/recovery_active_tasks.jsonl": "6ccca9ed1e69e4944f94fed8bec65044b1115286cd5001bfbcbc247049361d5f",
".modelhub_state/recovery_intents.jsonl": "94c0dfb993b526860e069526f5f207560caab842ab57603621f1ac0dd6ccb83b",
".modelhub_state/recent_outcomes.jsonl": "7c2662958c0ac747f257cd875beaae8d50ba1d8906059ef8dd0f40f93392eb0c",
".modelhub_state/recovery_active_tasks.jsonl": "5a7a40d44145835e34e3d5338bbfdbea3a32f74e6beaacba0a19f64094d9609f",
".modelhub_state/recovery_intents.jsonl": "7de958fbe8d37c834ca15cfd5eeb8c6fc7339261d081ef3cd4c48506aa910e45",
".modelhub_state/routing_intelligence.json": "a7d892e1ccda118f72a13ee212ed5aad3be9d65cdbf4c8218d696761745235b0",
".modelhub_state/submission_exclusions.jsonl": "a07e1a02840754257cdff556f0bbb75a93364d6fc493705741531a86b71b768e",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "369d50ba323fae299168a3afc0597ce8bc04a737b67af19154a569c0c08db4aa",
"outcomes/submissions.jsonl": "a00509eaa738324ec2fc7ceb1c100c26b5b13a3ab548148e1e7181a42aee1465"
},
"generation": 5540,
"generation": 5541,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-11T05:06:59.439889+00:00",
"updatedAt": "2026-09-11T05:09:56.122518+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}