state: generation 7173 (cycle)

This commit is contained in:
2026-09-14 12:29:04 +00:00
parent 3dcb77a3ca
commit 6d8a513bc2
9 changed files with 2130 additions and 2130 deletions

View File

@@ -1500,7 +1500,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-14T12:25:51.287842+00:00",
"generatedAt": "2026-09-14T12:29:03.827779+00:00",
"summary": {
"activeBlockCount": 75,
"byGpuFramework": {

View File

@@ -51,7 +51,7 @@
"4": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 521,
"listingErrors": 522,
"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": 4,
"nextAccountIndex": 5,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-14T12:25:51.261455+00:00",
"updatedAt": "2026-09-14T12:29:03.803609+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-14T12:23:48.464596+00:00",
"generatedAt": "2026-09-14T12:27:01.576596+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": "2026-09-14T12:08:31.465003+00:00",
"lastSyncTime": "2026-09-14T12:08:31.227289+00:00",
"generatedAt": "2026-09-14T12:26:52.708962+00:00",
"lastSyncTime": "2026-09-14T12:26:52.201763+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1661,13 +1661,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 47,
"failureBreakdown": {
"ambiguous_runtime": 36,
"ambiguous_runtime": 37,
"framework_architecture_unsupported": 43,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 2
},
"failureCount": 83,
"failureCount": 84,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1677,8 +1677,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 83,
"unresolvedFailureCount": 36
"total": 84,
"unresolvedFailureCount": 37
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 32,
@@ -2544,7 +2544,7 @@
"decisionSuccessRate": 0.0095,
"decisionTotal": 316,
"failureBreakdown": {
"ambiguous_runtime": 208,
"ambiguous_runtime": 209,
"backend_operator": 34,
"framework_architecture_unsupported": 224,
"memory_capacity": 7,
@@ -2555,15 +2555,15 @@
"tokenizer_compatibility": 7,
"参数/模板问题": 30
},
"failureCount": 552,
"failureCount": 553,
"failureRate": 0.9946,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0054,
"total": 555,
"unresolvedFailureCount": 238
"total": 556,
"unresolvedFailureCount": 239
},
"vllm-mlu": {
"attributableFailureCount": 8,
@@ -2670,7 +2670,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-14T12:08:31.457816+00:00",
"generatedAt": "2026-09-14T12:26:52.704480+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 34,
@@ -2701,7 +2701,7 @@
"decisionSuccessRate": 0.04,
"decisionTotal": 50,
"failureBreakdown": {
"ambiguous_runtime": 37,
"ambiguous_runtime": 38,
"framework_architecture_unsupported": 43,
"memory_capacity": 1,
"model_load": 1,
@@ -2710,15 +2710,15 @@
"参数/模板问题": 12,
"验证失败": 175
},
"failureCount": 272,
"failureCount": 273,
"failureRate": 0.9927,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0073,
"total": 274,
"unresolvedFailureCount": 224
"total": 275,
"unresolvedFailureCount": 225
},
"Biren_166m": {
"attributableFailureCount": 36,
@@ -4995,7 +4995,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T11:40:43.317618+00:00",
"lastTerminalAt": "2026-09-14T12:26:52.201763+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -8262,15 +8262,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1834,
"totalRecords": 1927,
"terminalRecords": 1835,
"totalRecords": 1928,
"totals": {
"attributableFailureCount": 551,
"decisionFailureRate": 0.9018,
"decisionSuccessRate": 0.0982,
"decisionTotal": 611,
"failureBreakdown": {
"ambiguous_runtime": 435,
"ambiguous_runtime": 436,
"backend_operator": 43,
"framework_architecture_unsupported": 350,
"memory_capacity": 12,
@@ -8282,15 +8282,15 @@
"参数/模板问题": 109,
"验证失败": 673
},
"failureCount": 1774,
"failureCount": 1775,
"failureRate": 0.9673,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 6,
"successCount": 60,
"successRate": 0.0327,
"total": 1834,
"unresolvedFailureCount": 1217
"total": 1835,
"unresolvedFailureCount": 1218
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -8328,6 +8328,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1927,
"summarizedRecords": 1928,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-14T12:26:52.201763+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T12:19:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4375377", "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": "2026-09-14T12:08:31.227267+00:00", "modelId": "callmezcc/Qwen3.8-27B-GPTQ-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T12:01:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4332825", "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": "2026-09-14T12:08:31.227289+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T12:01:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493489", "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": "2026-09-14T11:59:32.597701+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T11:57:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4575880", "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": "2026-09-09T22:49:15.213951+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:47:23+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471912", "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": "2026-09-09T22:49:15.213972+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:47:23+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471906", "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": "2026-09-09T22:06:26.296264+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:01:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493490", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T21:47:28.214740+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T21:41:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610342", "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": "575f65f2fc454fc2cb4f84e8bec4f948dbfc09592bea968ec533df63fab30145",
".modelhub_state/architecture_history_backfill.json": "b04b829aaeed0ebd4ac1986c24200c165affe133fb5f96581864df6ad091808b",
".modelhub_state/market_intelligence.json": "8c896e0bca758eb478d6db73190dd700798d89b642d36f1beba0f5f20fbfbc54",
".modelhub_state/official_capabilities.json": "051c74ef3041d8282c058c93cdeed530e62e000acfefea5b98ee1275a1b69e5d",
".modelhub_state/outcome_checkpoint.json": "4f75adbaffa3834814df131003657a4f6f24bd20191169d7a759ae725a68f196",
".modelhub_state/architecture_compatibility_blacklist.json": "c593b7b8b77965ba452e2dea08fd1c5bdd70942b161e7887eaf69bbc94ecdf50",
".modelhub_state/architecture_history_backfill.json": "d14773589a95997e0429c405933d7ff34e9300fa1bfaab5531fea03415f45ee5",
".modelhub_state/market_intelligence.json": "21f53153922ad4252d928bccfc9e7bd7d0cd3f4c4a0563ed82f9c6df3758c422",
".modelhub_state/official_capabilities.json": "c2362788ab5201ef900ad9b67a690e04020cc0f141d9b77fc46d313d72e5204f",
".modelhub_state/outcome_checkpoint.json": "e3a3836a13913ed33948821cab857a730e153f6e6bf75280156d4084a3a0f60e",
".modelhub_state/queue_cleanup_latest.json": "e5d9b334b2784235be02767778d1d31aa5d889dbe0cdb9bf65bb77a097c78531",
".modelhub_state/recent_outcomes.jsonl": "ac864ce16afb4ad6976fb2a686fa11073182a0950b802df9b8a8591e61c8cb84",
".modelhub_state/recovery_active_tasks.jsonl": "cccc7d2430d4e1d9e40bf910efcb0a04191faee2320195d0b2d868072b1ecf41",
".modelhub_state/recovery_intents.jsonl": "8b1fa743b088370d117b2070d18a3c3c62627c6c5b334fe5d80c1d319dc88267",
".modelhub_state/recent_outcomes.jsonl": "60280b1b5596ceb694c3234880bce9041d284246def41e6c336189e7e171d514",
".modelhub_state/recovery_active_tasks.jsonl": "a7f2a9f65f10930fd15ddfe3bda598e4aaf156e737f01531d6ac063c302784e3",
".modelhub_state/recovery_intents.jsonl": "aa42ac8ad730f1250f6802197e8652afc03519fd283b3e5ce9a617c0880f0e35",
".modelhub_state/routing_intelligence.json": "350794262038f5417f2c2055e35c53a6da870601a90b6c6b470484a8808e8764",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad",
"ledger/submissions.jsonl": "534da75337c614c3a3b5ecc6a07cf615533851ea1ac60f312bfbcce339099da3",
"outcomes/submissions.jsonl": "8a7f9b04e31b5c1244b75947509fbdf1e989f044d33aaacb9f35ef1eb6a740a7"
},
"generation": 7172,
"generation": 7173,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-14T12:25:51.387445+00:00",
"updatedAt": "2026-09-14T12:29:04.807616+00:00",
"writerId": "69701e73196b4ac2b3fad0f412335168"
}