state: generation 6004 (cycle)

This commit is contained in:
2026-09-12 03:34:42 +00:00
parent 01c85aae1e
commit 4ca13f4232
9 changed files with 2054 additions and 2051 deletions

View File

@@ -1345,7 +1345,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-12T03:31:35.007024+00:00",
"generatedAt": "2026-09-12T03:34:41.934002+00:00",
"summary": {
"activeBlockCount": 68,
"byGpuFramework": {

View File

@@ -35,7 +35,7 @@
"2": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 431,
"listingErrors": 432,
"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": 2,
"nextAccountIndex": 3,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-12T03:31:34.979887+00:00",
"updatedAt": "2026-09-12T03:34:41.908943+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T03:29:53.203954+00:00",
"generatedAt": "2026-09-12T03:32:42.118082+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": "2026-09-12T03:14:58.686149+00:00",
"lastSyncTime": "2026-09-12T03:14:58.435392+00:00",
"generatedAt": "2026-09-12T03:32:36.014119+00:00",
"lastSyncTime": "2026-09-12T03:32:35.805010+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1800,18 +1800,19 @@
"unresolvedFailureCount": 4
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 18,
"attributableFailureCount": 19,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 18,
"decisionTotal": 19,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 2,
"framework_architecture_unsupported": 9,
"model_load": 5,
"repository_structure": 1,
"runtime_memory": 2
},
"failureCount": 25,
"failureCount": 26,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1821,7 +1822,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 25,
"total": 26,
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
@@ -2376,10 +2377,10 @@
"unresolvedFailureCount": 862
},
"vllm": {
"attributableFailureCount": 250,
"decisionFailureRate": 0.9881,
"decisionSuccessRate": 0.0119,
"decisionTotal": 253,
"attributableFailureCount": 251,
"decisionFailureRate": 0.9882,
"decisionSuccessRate": 0.0118,
"decisionTotal": 254,
"failureBreakdown": {
"ambiguous_runtime": 195,
"backend_operator": 33,
@@ -2387,19 +2388,19 @@
"memory_capacity": 6,
"model_load": 21,
"platform_infrastructure": 1,
"repository_structure": 5,
"repository_structure": 6,
"runtime_memory": 6,
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 470,
"failureCount": 471,
"failureRate": 0.9937,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0063,
"total": 473,
"total": 474,
"unresolvedFailureCount": 219
},
"vllm-mlu": {
@@ -2504,7 +2505,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T03:14:58.681095+00:00",
"generatedAt": "2026-09-12T03:32:36.009482+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2643,27 +2644,28 @@
"unresolvedFailureCount": 27
},
"Iluvatar_bi-150": {
"attributableFailureCount": 23,
"decisionFailureRate": 0.7419,
"decisionSuccessRate": 0.2581,
"decisionTotal": 31,
"attributableFailureCount": 24,
"decisionFailureRate": 0.75,
"decisionSuccessRate": 0.25,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 12,
"backend_operator": 5,
"framework_architecture_unsupported": 10,
"model_load": 6,
"repository_structure": 1,
"runtime_memory": 2,
"参数/模板问题": 2,
"验证失败": 30
},
"failureCount": 67,
"failureRate": 0.8933,
"failureCount": 68,
"failureRate": 0.8947,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.1067,
"total": 75,
"successRate": 0.1053,
"total": 76,
"unresolvedFailureCount": 44
},
"Iluvatar_mrv-100": {
@@ -4413,23 +4415,24 @@
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 2,
"backend_operator": 1,
"framework_architecture_unsupported": 2,
"model_load": 2
"model_load": 2,
"repository_structure": 1
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T03:05:47.937930+00:00",
"lastTerminalAt": "2026-09-12T03:32:35.805010+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4437,7 +4440,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 7,
"total": 8,
"unresolvedFailureCount": 2
},
"Iluvatar_mrv-100|unknown|text-generation": {
@@ -4619,18 +4622,18 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 15,
"attributableFailureCount": 14,
"consecutiveFailures": 14,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 15,
"decisionTotal": 14,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"platform_infrastructure": 2,
"tokenizer_compatibility": 13
"tokenizer_compatibility": 12
},
"failureCount": 17,
"failureCount": 16,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-10T11:01:21+00:00",
@@ -4642,7 +4645,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 17,
"total": 16,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -7237,13 +7240,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1683,
"totalRecords": 1770,
"terminalRecords": 1684,
"totalRecords": 1771,
"totals": {
"attributableFailureCount": 455,
"decisionFailureRate": 0.8904,
"decisionSuccessRate": 0.1096,
"decisionTotal": 511,
"attributableFailureCount": 456,
"decisionFailureRate": 0.8906,
"decisionSuccessRate": 0.1094,
"decisionTotal": 512,
"failureBreakdown": {
"ambiguous_runtime": 394,
"backend_operator": 41,
@@ -7251,26 +7254,27 @@
"memory_capacity": 11,
"model_load": 65,
"platform_infrastructure": 4,
"repository_structure": 5,
"repository_structure": 6,
"runtime_memory": 6,
"tokenizer_compatibility": 47,
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1627,
"failureCount": 1628,
"failureRate": 0.9667,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 56,
"successRate": 0.0333,
"total": 1683,
"total": 1684,
"unresolvedFailureCount": 1168
},
"warnings": [
"GPU Ascend_910-b3 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 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 Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -7279,7 +7283,6 @@
"GPU MetaX_c-500 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 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 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。",
"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 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7301,6 +7304,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1770,
"summarizedRecords": 1771,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm", "lastSyncTime": "2026-09-12T03:32:35.805010+00:00", "modelId": "AI-ModelScope/bitnet-b1.58-2B-4T-bf16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T03:27:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080052", "taskType": "text-generation", "verifyResult": -1}
{"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": "2026-09-12T03:05:47.937930+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-Apollo-V0.1-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T03:05:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080040", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T03:05:47.937901+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:57:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4578245", "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", "framework": "vllm", "lastSyncTime": "2026-09-12T02:56:54.384007+00:00", "modelId": "amd/Qwen2.5-7B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:53:23+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079108", "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", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["zaya"], "framework": "vllm", "lastSyncTime": "2026-09-08T13:51:23.322084+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T13:31:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080030", "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", "framework": "vllm", "lastSyncTime": "2026-09-08T13:51:23.322046+00:00", "modelId": "amd/Qwen2.5_3B_Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T13:27:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080032", "taskType": "text-generation", "verifyResult": -1}
{"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": "2026-09-08T13:16:14.206250+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T12:59:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4133902", "taskType": "text-generation", "verifyResult": -1}
{"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": "2026-09-08T13:16:14.206275+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T12:57:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4107036", "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": "bf36d7d036a41f6833f691204bbd5f066a5f76c57964c4d4bc80ec76f674ba47",
".modelhub_state/architecture_history_backfill.json": "b439612ba37c98553973b035ebe009ccb642ca1654ed05dead309abd8034d66b",
".modelhub_state/market_intelligence.json": "54ec62a9edc15e8e35396370574b69e05a945b65b9b91d8c6ea4ff3522a144fc",
".modelhub_state/official_capabilities.json": "30fc5e604d9488ba8d6f64890ef703bf1ac30d161942f9d7b903b10788915b01",
".modelhub_state/outcome_checkpoint.json": "9753012387ccd8725b90dc8dadf78d80732ad221b079c0833759b9a82a8b3cc5",
".modelhub_state/architecture_compatibility_blacklist.json": "7c3dcc0dbfa96981c8502f756f68ebeec2cb344084e16c53fca1d60b59d85a9c",
".modelhub_state/architecture_history_backfill.json": "905ca75443fb66942738730c5c0b6911f877e93b19ea961d7d601135f295882a",
".modelhub_state/market_intelligence.json": "b3d3994f3e782fa434f465a497a8b1bed25e41322f904ecdd8668a95192c5490",
".modelhub_state/official_capabilities.json": "b9e29846b8d3eb191e38c48d71ddde8acee72858e2417606f9ad49a4f0158e03",
".modelhub_state/outcome_checkpoint.json": "ed0435b4cbb6597699fc56f007121df61503339d7dca221af2ef413bf6e45715",
".modelhub_state/queue_cleanup_latest.json": "dbff8ecbdcba815a2302661742ce4689464c0250a7ef3678d448f0d7a5dc07da",
".modelhub_state/recent_outcomes.jsonl": "990a39a1e8c54909aad06c81c05ba391c06836f39441ef09339da1eee45a8004",
".modelhub_state/recovery_active_tasks.jsonl": "764151d8b3a5e2aeeb16320dd884fa4b24e5599de31284f391913aaebb243104",
".modelhub_state/recovery_intents.jsonl": "434d61742675f8395a9bd9bb1263a7e42b66decdde5efca3a3d79d5dc9ca4541",
".modelhub_state/recent_outcomes.jsonl": "2cd4d0e1bf7192470d287bc12ec71d2ef6ca79b8c8ad84de1afbcc1c0fb47fd9",
".modelhub_state/recovery_active_tasks.jsonl": "c41c5be959f53c8c1ca8df4f996317898565ca14a7e50efe0531a76926ef8fa2",
".modelhub_state/recovery_intents.jsonl": "3407f64542f639c904b285db86df2cce0c2764c4ee9bfb4e44e0a8fa1929d5d9",
".modelhub_state/routing_intelligence.json": "316b7d02e32cf2dd3f7c0ca452f58d571a371863ac4d1c1b5193456035ce3a53",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "8abcf838f382e71b9140db2901b93972a33b043c4c67a56473d00af9ccd9be3c",
"outcomes/submissions.jsonl": "b51c060cb6f936826410b41fec62234d854cbfff601e5c0633b4704ccd24129c"
},
"generation": 6003,
"generation": 6004,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-12T03:31:35.176982+00:00",
"updatedAt": "2026-09-12T03:34:42.625293+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
}