state: generation 7469 (cycle)

This commit is contained in:
2026-09-15 01:36:09 +00:00
parent 2bca9680c4
commit 10c4b3f8e2
9 changed files with 2169 additions and 2169 deletions

View File

@@ -1558,7 +1558,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-15T01:33:12.545623+00:00",
"generatedAt": "2026-09-15T01:36:09.174955+00:00",
"summary": {
"activeBlockCount": 77,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 541,
"listingErrors": 542,
"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": "2026-09-15T01:33:12.520315+00:00",
"updatedAt": "2026-09-15T01:36:09.148479+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-15T01:31:24.597127+00:00",
"generatedAt": "2026-09-15T01:34:20.765355+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": "2026-09-15T01:15:42.552093+00:00",
"lastSyncTime": "2026-09-15T01:15:42.313690+00:00",
"generatedAt": "2026-09-15T01:34:13.292967+00:00",
"lastSyncTime": "2026-09-15T01:34:13.208356+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1790,9 +1790,9 @@
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 24,
"decisionFailureRate": 0.9231,
"decisionSuccessRate": 0.0769,
"decisionTotal": 26,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 27,
"failureBreakdown": {
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 21,
@@ -1802,16 +1802,16 @@
"验证失败": 39
},
"failureCount": 100,
"failureRate": 0.9804,
"failureRate": 0.9709,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0196,
"successCount": 3,
"successRate": 0.0291,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 102,
"total": 103,
"unresolvedFailureCount": 76
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
@@ -2576,9 +2576,9 @@
},
"unknown": {
"attributableFailureCount": 164,
"decisionFailureRate": 0.7455,
"decisionSuccessRate": 0.2545,
"decisionTotal": 220,
"decisionFailureRate": 0.7421,
"decisionSuccessRate": 0.2579,
"decisionTotal": 221,
"failureBreakdown": {
"ambiguous_runtime": 153,
"backend_operator": 4,
@@ -2591,13 +2591,13 @@
"验证失败": 673
},
"failureCount": 1057,
"failureRate": 0.9497,
"failureRate": 0.9488,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 56,
"successRate": 0.0503,
"total": 1113,
"successCount": 57,
"successRate": 0.0512,
"total": 1114,
"unresolvedFailureCount": 892
},
"vllm": {
@@ -2733,7 +2733,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-15T01:15:42.547474+00:00",
"generatedAt": "2026-09-15T01:34:13.247877+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 39,
@@ -2810,9 +2810,9 @@
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 24,
"decisionFailureRate": 0.9231,
"decisionSuccessRate": 0.0769,
"decisionTotal": 26,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 27,
"failureBreakdown": {
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 21,
@@ -2822,13 +2822,13 @@
"验证失败": 39
},
"failureCount": 100,
"failureRate": 0.9804,
"failureRate": 0.9709,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0196,
"total": 102,
"successCount": 3,
"successRate": 0.0291,
"total": 103,
"unresolvedFailureCount": 76
},
"Cambricon_mlu-370-x8": {
@@ -5446,31 +5446,31 @@
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 14,
"framework_architecture_unsupported": 3,
"tokenizer_compatibility": 1,
"参数/模板问题": 1
},
"failureCount": 20,
"failureRate": 1.0,
"failureCount": 19,
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-15T00:56:25.725574+00:00",
"lastTerminalAt": "2026-09-15T01:34:13.208356+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"successCount": 1,
"successRate": 0.05,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 16
"unresolvedFailureCount": 15
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -9129,13 +9129,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1887,
"totalRecords": 1980,
"terminalRecords": 1888,
"totalRecords": 1981,
"totals": {
"attributableFailureCount": 574,
"decisionFailureRate": 0.8997,
"decisionSuccessRate": 0.1003,
"decisionTotal": 638,
"decisionFailureRate": 0.8983,
"decisionSuccessRate": 0.1017,
"decisionTotal": 639,
"failureBreakdown": {
"ambiguous_runtime": 454,
"backend_operator": 44,
@@ -9150,13 +9150,13 @@
"验证失败": 673
},
"failureCount": 1823,
"failureRate": 0.9661,
"failureRate": 0.9656,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 6,
"successCount": 64,
"successRate": 0.0339,
"total": 1887,
"successCount": 65,
"successRate": 0.0344,
"total": 1888,
"unresolvedFailureCount": 1243
},
"warnings": [
@@ -9195,6 +9195,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1980,
"summarizedRecords": 1981,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-15T01:34:13.208356+00:00", "modelId": "OpenOneRec/OneReason-8B-pretrain-competition", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-15T01:27:22+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4584699", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "", "lastSyncTime": "2026-09-15T01:15:42.313690+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T01:15:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4588142", "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": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-15T00:56:25.725574+00:00", "modelId": "callmezcc/Qwen3.8-27B-GPTQ-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:53:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4332632", "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"], "framework": "vllm", "lastSyncTime": "2026-09-15T00:40:39.932460+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:33:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4591815", "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": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T04:27:58.701457+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:21:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471915", "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": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-10T04:09:13.117076+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:01:22+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4609102", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-10T04:00:09.998782+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T03:57:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532022", "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": "2026-09-10T02:50:12.317776+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:43:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493607", "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": "4bf9a207dccda2fb7b9014de01b95ee7c6e550bf50b91ce04a4deb1419c556f0",
".modelhub_state/architecture_history_backfill.json": "19b7379c0885ca3e86f1536c287e8ec4a6e385270639304e9d13ff13cb936017",
".modelhub_state/market_intelligence.json": "652240b2c34a06af7388ee4d8b1781479fbecbb1c5c912639c4992932198ad9e",
".modelhub_state/official_capabilities.json": "37d57a9b0c6210e8dd9849fa1cead63c56569ae7cb7f1a07307e236cfe914f10",
".modelhub_state/outcome_checkpoint.json": "a6e8e6b5ca82000ce43901c9024c6c43532b82cffc88d13f345db3e590482fe6",
".modelhub_state/architecture_compatibility_blacklist.json": "127dc8a074886f3bc20076d30ed1d573c30dd0e59c2b254260274b646e481c99",
".modelhub_state/architecture_history_backfill.json": "12f983a940a29fb4383aa5bc80c377b57f95b6cdc756d74395dad4bae984ce36",
".modelhub_state/market_intelligence.json": "1c9a2498d06eb5d921d4e2b0367c693461cb3dfb32c4b1ead4ecea9e390842ad",
".modelhub_state/official_capabilities.json": "b6869b0d01889e77337ea1358a3ca2127829ed420e9f21ea9a69e054a1c6dfbe",
".modelhub_state/outcome_checkpoint.json": "b2d6674e18acc0bd4554220176e6a77696a637f0daf97fa55428762188e81fc1",
".modelhub_state/queue_cleanup_latest.json": "01e08fd4618eb925c85708b1e84308d8914f762fc7ce784e5b71b8af21bef866",
".modelhub_state/recent_outcomes.jsonl": "03b019cf5ff6c06d66cd5a0782f7f0bb16da4bbf09f73f0032ba7949734e28ec",
".modelhub_state/recovery_active_tasks.jsonl": "0d5374924d2a1d461ea29ce5737ca86dd952642a4cac6a04e94b8a6cf6cf3a80",
".modelhub_state/recovery_intents.jsonl": "41e44e9b983d681236616fdec9f170deb4de8b40c6265c33cf5e12d1043f0be6",
".modelhub_state/recent_outcomes.jsonl": "93705c2fc470e099e7dadea866be64b6fac982255f4333ba1d318d59bf7f3b10",
".modelhub_state/recovery_active_tasks.jsonl": "a8dbe478b964a5fee27f33896c2bf749c8a3cfe2dff1e703921f60d9835f1bc5",
".modelhub_state/recovery_intents.jsonl": "5c4994f5fc155419ebbf566611d2222fbcfd9b818103b1e3991bbcba21f2ef7d",
".modelhub_state/routing_intelligence.json": "5f7939a4bcc0cd3361fb3c8b9e46d01882b7482b42018a697367e830f28b1f09",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "b8563512d893ae2a4f8a4d65881d0eab34d0b8d937550ac1fd54cdbaddb9db2b",
"outcomes/submissions.jsonl": "284474ecc34a1929ae1231026b241ced0608ac5195030271a98deb230c5146c4"
},
"generation": 7468,
"generation": 7469,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-15T01:33:12.631458+00:00",
"updatedAt": "2026-09-15T01:36:09.895970+00:00",
"writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c"
}