state: generation 5125 (cycle)
This commit is contained in:
@@ -580,7 +580,7 @@
|
|||||||
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5_moe": {
|
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5_moe": {
|
||||||
"architectureSignature": "model_type:qwen3_5_moe",
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
"architectures": [],
|
"architectures": [],
|
||||||
"evidenceCount": 2,
|
"evidenceCount": 1,
|
||||||
"expiresAt": "2026-10-07T23:51:21+00:00",
|
"expiresAt": "2026-10-07T23:51:21+00:00",
|
||||||
"framework": "vllm",
|
"framework": "vllm",
|
||||||
"latestFailureAt": "2026-09-07T23:51:21+00:00",
|
"latestFailureAt": "2026-09-07T23:51:21+00:00",
|
||||||
@@ -588,12 +588,10 @@
|
|||||||
"matchType": "model_type",
|
"matchType": "model_type",
|
||||||
"modelType": "qwen3_5_moe",
|
"modelType": "qwen3_5_moe",
|
||||||
"sourceModelIds": [
|
"sourceModelIds": [
|
||||||
"mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B",
|
"mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B"
|
||||||
"mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B"
|
|
||||||
],
|
],
|
||||||
"sourceTaskIds": [
|
"sourceTaskIds": [
|
||||||
"4479115",
|
"4479115"
|
||||||
"4482387"
|
|
||||||
],
|
],
|
||||||
"targetGpu": "hygon_k100-ai",
|
"targetGpu": "hygon_k100-ai",
|
||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
@@ -1317,7 +1315,7 @@
|
|||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-09-10T10:45:38.741934+00:00",
|
"generatedAt": "2026-09-10T10:50:20.891763+00:00",
|
||||||
"summary": {
|
"summary": {
|
||||||
"activeBlockCount": 66,
|
"activeBlockCount": 66,
|
||||||
"byGpuFramework": {
|
"byGpuFramework": {
|
||||||
|
|||||||
@@ -11,7 +11,7 @@
|
|||||||
"1": {
|
"1": {
|
||||||
"complete": false,
|
"complete": false,
|
||||||
"lastError": "ModelHubAPIError: 系统错误",
|
"lastError": "ModelHubAPIError: 系统错误",
|
||||||
"listingErrors": 364,
|
"listingErrors": 365,
|
||||||
"nextPage": 1,
|
"nextPage": 1,
|
||||||
"recordsScanned": 0,
|
"recordsScanned": 0,
|
||||||
"uniqueRecords": 0
|
"uniqueRecords": 0
|
||||||
@@ -102,12 +102,12 @@
|
|||||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||||
"failureLogsInspected": 0,
|
"failureLogsInspected": 0,
|
||||||
"mode": "incremental_decision_only",
|
"mode": "incremental_decision_only",
|
||||||
"nextAccountIndex": 1,
|
"nextAccountIndex": 2,
|
||||||
"recordsScanned": 0,
|
"recordsScanned": 0,
|
||||||
"seenTaskIds": [],
|
"seenTaskIds": [],
|
||||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||||
"terminalRecords": 0,
|
"terminalRecords": 0,
|
||||||
"uniqueRecords": 0,
|
"uniqueRecords": 0,
|
||||||
"updatedAt": "2026-09-10T10:45:38.719110+00:00",
|
"updatedAt": "2026-09-10T10:50:20.868266+00:00",
|
||||||
"version": 1
|
"version": 1
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -1,8 +1,8 @@
|
|||||||
{
|
{
|
||||||
"communityAttemptedAt": "2026-09-10T10:30:10.779571+00:00",
|
"communityAttemptedAt": "2026-09-10T10:46:46.609440+00:00",
|
||||||
"communityError": null,
|
"communityError": null,
|
||||||
"communitySample": {},
|
"communitySample": {},
|
||||||
"communityUpdatedAt": "2026-09-10T10:30:10.779571+00:00",
|
"communityUpdatedAt": "2026-09-10T10:46:46.609440+00:00",
|
||||||
"frameworkAttemptedAt": "2026-09-10T06:33:41.338309+00:00",
|
"frameworkAttemptedAt": "2026-09-10T06:33:41.338309+00:00",
|
||||||
"frameworkError": null,
|
"frameworkError": null,
|
||||||
"frameworkStats": {
|
"frameworkStats": {
|
||||||
@@ -416,121 +416,121 @@
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
"frameworkUpdatedAt": null,
|
"frameworkUpdatedAt": null,
|
||||||
"generatedAt": "2026-09-10T10:44:12.144314+00:00",
|
"generatedAt": "2026-09-10T10:46:46.609440+00:00",
|
||||||
"gpuStats": {
|
"gpuStats": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 955.6326530612245,
|
"backlogHours": 1010.4604316546762,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Ascend_910-b3",
|
"gpu": "Ascend_910-b3",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 8,
|
"maxConcurrentTasks": 8,
|
||||||
"qualityFactor": 1.5360089198751359,
|
"qualityFactor": 1.5364993544246883,
|
||||||
"queueFactor": 0.9633427071060552,
|
"queueFactor": 0.9582411609965127,
|
||||||
"queueWeight": 0.9633427071060552,
|
"queueWeight": 0.9582411609965127,
|
||||||
"recentSuccess": 62,
|
"recentSuccess": 61,
|
||||||
"recentSuccessRate": 0.4217687074829932,
|
"recentSuccessRate": 0.43884892086330934,
|
||||||
"recentTerminal": 147,
|
"recentTerminal": 139,
|
||||||
"recentWilsonLowerBound": 0.3449255137872042,
|
"recentWilsonLowerBound": 0.35909532617597445,
|
||||||
"running": 8,
|
"running": 8,
|
||||||
"selectionWeight": 1.479702991011561,
|
"selectionWeight": 1.4723369252543055,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 24.5,
|
"throughputPerHour": 23.166666666666668,
|
||||||
"waiting": 23413
|
"waiting": 23409
|
||||||
},
|
},
|
||||||
"Ascend_910-b4": {
|
"Ascend_910-b4": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 998.9090909090909,
|
"backlogHours": 987.0538922155689,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Ascend_910-b4",
|
"gpu": "Ascend_910-b4",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 8,
|
"maxConcurrentTasks": 8,
|
||||||
"qualityFactor": 0.7145988597084797,
|
"qualityFactor": 0.702203699175548,
|
||||||
"queueFactor": 0.9569639247452255,
|
"queueFactor": 0.9616157964884233,
|
||||||
"queueWeight": 0.9569639247452255,
|
"queueWeight": 0.9616157964884233,
|
||||||
"recentSuccess": 51,
|
"recentSuccess": 53,
|
||||||
"recentSuccessRate": 0.3090909090909091,
|
"recentSuccessRate": 0.31736526946107785,
|
||||||
"recentTerminal": 165,
|
"recentTerminal": 167,
|
||||||
"recentWilsonLowerBound": 0.24359343748041754,
|
"recentWilsonLowerBound": 0.2515549178173127,
|
||||||
"running": 8,
|
"running": 8,
|
||||||
"selectionWeight": 0.6838453294050896,
|
"selectionWeight": 0.6752501694798119,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 27.5,
|
"throughputPerHour": 27.833333333333332,
|
||||||
"waiting": 27470
|
"waiting": 27473
|
||||||
},
|
},
|
||||||
"Biren_166m": {
|
"Biren_166m": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 133.61194029850745,
|
"backlogHours": 130.8,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Biren_166m",
|
"gpu": "Biren_166m",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 8,
|
"maxConcurrentTasks": 8,
|
||||||
"qualityFactor": 0.21445357420015781,
|
"qualityFactor": 0.21436382825880457,
|
||||||
"queueFactor": 1.2940399089509387,
|
"queueFactor": 1.3,
|
||||||
"queueWeight": 1.2940399089509387,
|
"queueWeight": 1.3,
|
||||||
"recentSuccess": 38,
|
"recentSuccess": 40,
|
||||||
"recentSuccessRate": 0.1890547263681592,
|
"recentSuccessRate": 0.1951219512195122,
|
||||||
"recentTerminal": 201,
|
"recentTerminal": 205,
|
||||||
"recentWilsonLowerBound": 0.1409488313854867,
|
"recentWilsonLowerBound": 0.14668991695050224,
|
||||||
"running": 8,
|
"running": 8,
|
||||||
"selectionWeight": 0.2775114836321756,
|
"selectionWeight": 0.2786729767364459,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 33.5,
|
"throughputPerHour": 34.166666666666664,
|
||||||
"waiting": 4476
|
"waiting": 4469
|
||||||
},
|
},
|
||||||
"Cambricon_mlu-370-x4": {
|
"Cambricon_mlu-370-x4": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 966.2727272727274,
|
"backlogHours": 934.4835164835165,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Cambricon_mlu-370-x4",
|
"gpu": "Cambricon_mlu-370-x4",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 7,
|
"maxConcurrentTasks": 7,
|
||||||
"qualityFactor": 0.11482527833201761,
|
"qualityFactor": 0.09745147020456013,
|
||||||
"queueFactor": 0.9617440381026086,
|
"queueFactor": 0.9695427695399969,
|
||||||
"queueWeight": 0.9617440381026086,
|
"queueWeight": 0.9695427695399969,
|
||||||
"recentSuccess": 15,
|
"recentSuccess": 15,
|
||||||
"recentSuccessRate": 0.17045454545454544,
|
"recentSuccessRate": 0.16483516483516483,
|
||||||
"recentTerminal": 88,
|
"recentTerminal": 91,
|
||||||
"recentWilsonLowerBound": 0.10610728809302103,
|
"recentWilsonLowerBound": 0.10251340708451503,
|
||||||
"running": 7,
|
"running": 7,
|
||||||
"selectionWeight": 0.11043252685929057,
|
"selectionWeight": 0.09448336831787371,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 14.666666666666666,
|
"throughputPerHour": 15.166666666666666,
|
||||||
"waiting": 14172
|
"waiting": 14173
|
||||||
},
|
},
|
||||||
"Cambricon_mlu-370-x8": {
|
"Cambricon_mlu-370-x8": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 510.0576923076923,
|
"backlogHours": 495.8691588785047,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Cambricon_mlu-370-x8",
|
"gpu": "Cambricon_mlu-370-x8",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 7,
|
"maxConcurrentTasks": 7,
|
||||||
"qualityFactor": 0.4719035331371323,
|
"qualityFactor": 0.4429308513957569,
|
||||||
"queueFactor": 1.0584773419017235,
|
"queueFactor": 1.0662220360766055,
|
||||||
"queueWeight": 1.0584773419017235,
|
"queueWeight": 1.0662220360766055,
|
||||||
"recentSuccess": 29,
|
"recentSuccess": 30,
|
||||||
"recentSuccessRate": 0.27884615384615385,
|
"recentSuccessRate": 0.2803738317757009,
|
||||||
"recentTerminal": 104,
|
"recentTerminal": 107,
|
||||||
"recentWilsonLowerBound": 0.20172158008187036,
|
"recentWilsonLowerBound": 0.20401679054167657,
|
||||||
"running": 7,
|
"running": 7,
|
||||||
"selectionWeight": 0.49949919738902365,
|
"selectionWeight": 0.4722626342163283,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 17.333333333333332,
|
"throughputPerHour": 17.833333333333332,
|
||||||
"waiting": 8841
|
"waiting": 8843
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-100": {
|
"Iluvatar_bi-100": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 41.33720930232558,
|
"backlogHours": 41.91150442477876,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Iluvatar_bi-100",
|
"gpu": "Iluvatar_bi-100",
|
||||||
@@ -540,125 +540,125 @@
|
|||||||
"queueFactor": 1.3,
|
"queueFactor": 1.3,
|
||||||
"queueWeight": 1.3,
|
"queueWeight": 1.3,
|
||||||
"recentSuccess": 23,
|
"recentSuccess": 23,
|
||||||
"recentSuccessRate": 0.06686046511627906,
|
"recentSuccessRate": 0.06784660766961652,
|
||||||
"recentTerminal": 344,
|
"recentTerminal": 339,
|
||||||
"recentWilsonLowerBound": 0.04496215097777923,
|
"recentWilsonLowerBound": 0.045631573892276754,
|
||||||
"running": 1,
|
"running": 6,
|
||||||
"selectionWeight": 0.065,
|
"selectionWeight": 0.065,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": false,
|
"submissionEligible": false,
|
||||||
"throughputPerHour": 57.333333333333336,
|
"throughputPerHour": 56.5,
|
||||||
"waiting": 2370
|
"waiting": 2368
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150": {
|
"Iluvatar_bi-150": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 66.27586206896552,
|
"backlogHours": 66.72832369942196,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Iluvatar_bi-150",
|
"gpu": "Iluvatar_bi-150",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 50,
|
"maxConcurrentTasks": 50,
|
||||||
"qualityFactor": 0.11979625270012861,
|
"qualityFactor": 0.1110995471437636,
|
||||||
"queueFactor": 1.3,
|
"queueFactor": 1.3,
|
||||||
"queueWeight": 1.3,
|
"queueWeight": 1.3,
|
||||||
"recentSuccess": 49,
|
"recentSuccess": 49,
|
||||||
"recentSuccessRate": 0.14080459770114942,
|
"recentSuccessRate": 0.1416184971098266,
|
||||||
"recentTerminal": 348,
|
"recentTerminal": 346,
|
||||||
"recentWilsonLowerBound": 0.10817115183410501,
|
"recentWilsonLowerBound": 0.10880658121758911,
|
||||||
"running": 4,
|
"running": 1,
|
||||||
"selectionWeight": 0.15573512851016721,
|
"selectionWeight": 0.14442941128689268,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 58.0,
|
"throughputPerHour": 57.666666666666664,
|
||||||
"waiting": 3844
|
"waiting": 3848
|
||||||
},
|
},
|
||||||
"Iluvatar_mrv-100": {
|
"Iluvatar_mrv-100": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 2211.4285714285716,
|
"backlogHours": 2110.7727272727275,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Iluvatar_mrv-100",
|
"gpu": "Iluvatar_mrv-100",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 2,
|
"maxConcurrentTasks": 2,
|
||||||
"qualityFactor": 0.06717198935337282,
|
"qualityFactor": 0.08266821124355733,
|
||||||
"queueFactor": 0.8494220363732773,
|
"queueFactor": 0.8579984387158612,
|
||||||
"queueWeight": 0.8494220363732773,
|
"queueWeight": 0.8579984387158612,
|
||||||
"recentSuccess": 7,
|
"recentSuccess": 8,
|
||||||
"recentSuccessRate": 0.16666666666666666,
|
"recentSuccessRate": 0.18181818181818182,
|
||||||
"recentTerminal": 42,
|
"recentTerminal": 44,
|
||||||
"recentWilsonLowerBound": 0.08315811295836503,
|
"recentWilsonLowerBound": 0.09512692558258554,
|
||||||
"running": 2,
|
"running": 2,
|
||||||
"selectionWeight": 0.05705736798378604,
|
"selectionWeight": 0.0709291961784052,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 7.0,
|
"throughputPerHour": 7.333333333333333,
|
||||||
"waiting": 15480
|
"waiting": 15479
|
||||||
},
|
},
|
||||||
"Kunlunxin_p-800": {
|
"Kunlunxin_p-800": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 652.4399999999999,
|
"backlogHours": 659.030303030303,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Kunlunxin_p-800",
|
"gpu": "Kunlunxin_p-800",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 7,
|
"maxConcurrentTasks": 7,
|
||||||
"qualityFactor": 0.24596516988239922,
|
"qualityFactor": 0.20309868027291925,
|
||||||
"queueFactor": 1.0201014718866421,
|
"queueFactor": 1.0216847500388697,
|
||||||
"queueWeight": 1.0201014718866421,
|
"queueWeight": 1.0216847500388697,
|
||||||
"recentSuccess": 22,
|
"recentSuccess": 21,
|
||||||
"recentSuccessRate": 0.22,
|
"recentSuccessRate": 0.21212121212121213,
|
||||||
"recentTerminal": 100,
|
"recentTerminal": 99,
|
||||||
"recentWilsonLowerBound": 0.15001174503655804,
|
"recentWilsonLowerBound": 0.14313429916193274,
|
||||||
"running": 7,
|
"running": 7,
|
||||||
"selectionWeight": 0.2509094318298834,
|
"selectionWeight": 0.20750282438786183,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 16.666666666666668,
|
"throughputPerHour": 16.5,
|
||||||
"waiting": 10874
|
"waiting": 10874
|
||||||
},
|
},
|
||||||
"MetaX_c-500": {
|
"MetaX_c-500": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 635.8333333333334,
|
"backlogHours": 612.75,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "MetaX_c-500",
|
"gpu": "MetaX_c-500",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 4,
|
"maxConcurrentTasks": 4,
|
||||||
"qualityFactor": 0.5166014296437633,
|
"qualityFactor": 0.4732354691301979,
|
||||||
"queueFactor": 1.0240542569928832,
|
"queueFactor": 1.0329046217901328,
|
||||||
"queueWeight": 1.0240542569928832,
|
"queueWeight": 1.0329046217901328,
|
||||||
"recentSuccess": 31,
|
"recentSuccess": 32,
|
||||||
"recentSuccessRate": 0.28703703703703703,
|
"recentSuccessRate": 0.2857142857142857,
|
||||||
"recentTerminal": 108,
|
"recentTerminal": 112,
|
||||||
"recentWilsonLowerBound": 0.21019243295848952,
|
"recentWilsonLowerBound": 0.21024717263298542,
|
||||||
"running": 4,
|
"running": 4,
|
||||||
"selectionWeight": 0.5290278931953053,
|
"selectionWeight": 0.48880710325960314,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 18.0,
|
"throughputPerHour": 18.666666666666668,
|
||||||
"waiting": 11445
|
"waiting": 11438
|
||||||
},
|
},
|
||||||
"Mthreads_s4000": {
|
"Mthreads_s4000": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 1667.6883116883116,
|
"backlogHours": 1625.012658227848,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Mthreads_s4000",
|
"gpu": "Mthreads_s4000",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 4,
|
"maxConcurrentTasks": 4,
|
||||||
"qualityFactor": 0.9458295551936025,
|
"qualityFactor": 0.8156223522289983,
|
||||||
"queueFactor": 0.8861499724572364,
|
"queueFactor": 0.8923273542081046,
|
||||||
"queueWeight": 0.8861499724572364,
|
"queueWeight": 0.8923273542081046,
|
||||||
"recentSuccess": 29,
|
"recentSuccess": 29,
|
||||||
"recentSuccessRate": 0.37662337662337664,
|
"recentSuccessRate": 0.3670886075949367,
|
||||||
"recentTerminal": 77,
|
"recentTerminal": 79,
|
||||||
"recentWilsonLowerBound": 0.27669846411806526,
|
"recentWilsonLowerBound": 0.26927131273817784,
|
||||||
"running": 4,
|
"running": 4,
|
||||||
"selectionWeight": 0.8381468342840509,
|
"selectionWeight": 0.7278021355974927,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 12.833333333333334,
|
"throughputPerHour": 13.166666666666666,
|
||||||
"waiting": 21402
|
"waiting": 21396
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1": {
|
"Sunrise_pt-200-x1": {
|
||||||
"available": true,
|
"available": true,
|
||||||
@@ -668,15 +668,15 @@
|
|||||||
"gpu": "Sunrise_pt-200-x1",
|
"gpu": "Sunrise_pt-200-x1",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 2,
|
"maxConcurrentTasks": 2,
|
||||||
"qualityFactor": 1.0601994508988286,
|
"qualityFactor": 0.9706451020437092,
|
||||||
"queueFactor": 0.7222624020060023,
|
"queueFactor": 0.7244747697358538,
|
||||||
"queueWeight": 0.7222624020060023,
|
"queueWeight": 0.7244747697358538,
|
||||||
"recentSuccess": 7,
|
"recentSuccess": 7,
|
||||||
"recentSuccessRate": 0.5384615384615384,
|
"recentSuccessRate": 0.5384615384615384,
|
||||||
"recentTerminal": 13,
|
"recentTerminal": 13,
|
||||||
"recentWilsonLowerBound": 0.29143432431832045,
|
"recentWilsonLowerBound": 0.29143432431832045,
|
||||||
"running": 2,
|
"running": 2,
|
||||||
"selectionWeight": 0.7657422020116327,
|
"selectionWeight": 0.7032078867983506,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": false,
|
"submissionEligible": false,
|
||||||
"throughputPerHour": 2.1666666666666665,
|
"throughputPerHour": 2.1666666666666665,
|
||||||
@@ -684,52 +684,52 @@
|
|||||||
},
|
},
|
||||||
"Vastai_va16": {
|
"Vastai_va16": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 837.5833333333334,
|
"backlogHours": 861.6857142857143,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Vastai_va16",
|
"gpu": "Vastai_va16",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 16,
|
"maxConcurrentTasks": 16,
|
||||||
"qualityFactor": 0.5898734142507962,
|
"qualityFactor": 0.44939378159932514,
|
||||||
"queueFactor": 0.9825852874378418,
|
"queueFactor": 0.9814097873026633,
|
||||||
"queueWeight": 0.9825852874378418,
|
"queueWeight": 0.9814097873026633,
|
||||||
"recentSuccess": 23,
|
"recentSuccess": 21,
|
||||||
"recentSuccessRate": 0.3194444444444444,
|
"recentSuccessRate": 0.3,
|
||||||
"recentTerminal": 72,
|
"recentTerminal": 70,
|
||||||
"recentWilsonLowerBound": 0.2232545704855647,
|
"recentWilsonLowerBound": 0.20536456738510148,
|
||||||
"running": 16,
|
"running": 16,
|
||||||
"selectionWeight": 0.5796009382935597,
|
"selectionWeight": 0.44103945561453317,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 12.0,
|
"throughputPerHour": 11.666666666666666,
|
||||||
"waiting": 10051
|
"waiting": 10053
|
||||||
},
|
},
|
||||||
"hygon_k100-ai": {
|
"hygon_k100-ai": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 469.18918918918916,
|
"backlogHours": 469.0810810810811,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "hygon_k100-ai",
|
"gpu": "hygon_k100-ai",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 6,
|
"maxConcurrentTasks": 6,
|
||||||
"qualityFactor": 2.5,
|
"qualityFactor": 2.5,
|
||||||
"queueFactor": 1.071820999251822,
|
"queueFactor": 1.0751412656113561,
|
||||||
"queueWeight": 1.071820999251822,
|
"queueWeight": 1.0751412656113561,
|
||||||
"recentSuccess": 58,
|
"recentSuccess": 60,
|
||||||
"recentSuccessRate": 0.5225225225225225,
|
"recentSuccessRate": 0.5405405405405406,
|
||||||
"recentTerminal": 111,
|
"recentTerminal": 111,
|
||||||
"recentWilsonLowerBound": 0.43041035948715833,
|
"recentWilsonLowerBound": 0.44802693921571074,
|
||||||
"running": 6,
|
"running": 6,
|
||||||
"selectionWeight": 2.6795524981295546,
|
"selectionWeight": 2.6878531640283905,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 18.5,
|
"throughputPerHour": 18.5,
|
||||||
"waiting": 8680
|
"waiting": 8678
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"queueAttemptedAt": "2026-09-10T10:35:56.867263+00:00",
|
"queueAttemptedAt": "2026-09-10T10:46:46.609440+00:00",
|
||||||
"queueError": null,
|
"queueError": null,
|
||||||
"queueUpdatedAt": "2026-09-10T10:35:56.867263+00:00",
|
"queueUpdatedAt": "2026-09-10T10:46:46.609440+00:00",
|
||||||
"supportedGpus": [
|
"supportedGpus": [
|
||||||
"Vastai_va16",
|
"Vastai_va16",
|
||||||
"Iluvatar_mrv-100",
|
"Iluvatar_mrv-100",
|
||||||
|
|||||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"generatedAt": "2026-09-10T10:30:02.798435+00:00",
|
"generatedAt": "2026-09-10T10:46:39.673314+00:00",
|
||||||
"lastSyncTime": "2026-09-10T10:30:02.547307+00:00",
|
"lastSyncTime": "2026-09-10T10:46:39.406893+00:00",
|
||||||
"recentLimit": 300,
|
"recentLimit": 300,
|
||||||
"report": {
|
"report": {
|
||||||
"architectureCompatibilityBlocks": {
|
"architectureCompatibilityBlocks": {
|
||||||
@@ -584,7 +584,7 @@
|
|||||||
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5_moe": {
|
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5_moe": {
|
||||||
"architectureSignature": "model_type:qwen3_5_moe",
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
"architectures": [],
|
"architectures": [],
|
||||||
"evidenceCount": 2,
|
"evidenceCount": 1,
|
||||||
"expiresAt": "2026-10-07T23:51:21+00:00",
|
"expiresAt": "2026-10-07T23:51:21+00:00",
|
||||||
"framework": "vllm",
|
"framework": "vllm",
|
||||||
"latestFailureAt": "2026-09-07T23:51:21+00:00",
|
"latestFailureAt": "2026-09-07T23:51:21+00:00",
|
||||||
@@ -592,12 +592,10 @@
|
|||||||
"matchType": "model_type",
|
"matchType": "model_type",
|
||||||
"modelType": "qwen3_5_moe",
|
"modelType": "qwen3_5_moe",
|
||||||
"sourceModelIds": [
|
"sourceModelIds": [
|
||||||
"mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B",
|
"mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B"
|
||||||
"mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B"
|
|
||||||
],
|
],
|
||||||
"sourceTaskIds": [
|
"sourceTaskIds": [
|
||||||
"4479115",
|
"4479115"
|
||||||
"4482387"
|
|
||||||
],
|
],
|
||||||
"targetGpu": "hygon_k100-ai",
|
"targetGpu": "hygon_k100-ai",
|
||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
@@ -2050,17 +2048,17 @@
|
|||||||
"unresolvedFailureCount": 33
|
"unresolvedFailureCount": 33
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||||
"attributableFailureCount": 29,
|
"attributableFailureCount": 30,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 29,
|
"decisionTotal": 30,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"framework_architecture_unsupported": 2,
|
"framework_architecture_unsupported": 2,
|
||||||
"platform_infrastructure": 1,
|
"platform_infrastructure": 1,
|
||||||
"tokenizer_compatibility": 27,
|
"tokenizer_compatibility": 28,
|
||||||
"参数/模板问题": 6
|
"参数/模板问题": 6
|
||||||
},
|
},
|
||||||
"failureCount": 36,
|
"failureCount": 37,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_fix_tokenizer",
|
"framework": "vllm_fix_tokenizer",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
@@ -2070,7 +2068,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Sunrise_pt-200-x1",
|
"targetGpu": "Sunrise_pt-200-x1",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 36,
|
"total": 37,
|
||||||
"unresolvedFailureCount": 6
|
"unresolvedFailureCount": 6
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||||
@@ -2406,26 +2404,26 @@
|
|||||||
"unresolvedFailureCount": 3
|
"unresolvedFailureCount": 3
|
||||||
},
|
},
|
||||||
"vllm_fix_tokenizer": {
|
"vllm_fix_tokenizer": {
|
||||||
"attributableFailureCount": 32,
|
"attributableFailureCount": 33,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 32,
|
"decisionTotal": 33,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 29,
|
"ambiguous_runtime": 29,
|
||||||
"framework_architecture_unsupported": 4,
|
"framework_architecture_unsupported": 4,
|
||||||
"model_load": 1,
|
"model_load": 1,
|
||||||
"platform_infrastructure": 1,
|
"platform_infrastructure": 1,
|
||||||
"tokenizer_compatibility": 27,
|
"tokenizer_compatibility": 28,
|
||||||
"参数/模板问题": 7
|
"参数/模板问题": 7
|
||||||
},
|
},
|
||||||
"failureCount": 69,
|
"failureCount": 70,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 1,
|
"platformFailureCount": 1,
|
||||||
"successCount": 0,
|
"successCount": 0,
|
||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"total": 69,
|
"total": 70,
|
||||||
"unresolvedFailureCount": 36
|
"unresolvedFailureCount": 36
|
||||||
},
|
},
|
||||||
"vllm_tokenizer_patch": {
|
"vllm_tokenizer_patch": {
|
||||||
@@ -2447,7 +2445,7 @@
|
|||||||
"unresolvedFailureCount": 1
|
"unresolvedFailureCount": 1
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-09-10T10:30:02.793656+00:00",
|
"generatedAt": "2026-09-10T10:46:39.668682+00:00",
|
||||||
"gpuSummaries": {
|
"gpuSummaries": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"attributableFailureCount": 26,
|
"attributableFailureCount": 26,
|
||||||
@@ -2704,25 +2702,25 @@
|
|||||||
"unresolvedFailureCount": 59
|
"unresolvedFailureCount": 59
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1": {
|
"Sunrise_pt-200-x1": {
|
||||||
"attributableFailureCount": 30,
|
"attributableFailureCount": 31,
|
||||||
"decisionFailureRate": 0.9677,
|
"decisionFailureRate": 0.9688,
|
||||||
"decisionSuccessRate": 0.0323,
|
"decisionSuccessRate": 0.0312,
|
||||||
"decisionTotal": 31,
|
"decisionTotal": 32,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"framework_architecture_unsupported": 3,
|
"framework_architecture_unsupported": 3,
|
||||||
"platform_infrastructure": 2,
|
"platform_infrastructure": 2,
|
||||||
"tokenizer_compatibility": 27,
|
"tokenizer_compatibility": 28,
|
||||||
"参数/模板问题": 9,
|
"参数/模板问题": 9,
|
||||||
"验证失败": 32
|
"验证失败": 32
|
||||||
},
|
},
|
||||||
"failureCount": 73,
|
"failureCount": 74,
|
||||||
"failureRate": 0.9865,
|
"failureRate": 0.9867,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 2,
|
"platformFailureCount": 2,
|
||||||
"successCount": 1,
|
"successCount": 1,
|
||||||
"successRate": 0.0135,
|
"successRate": 0.0133,
|
||||||
"total": 74,
|
"total": 75,
|
||||||
"unresolvedFailureCount": 41
|
"unresolvedFailureCount": 41
|
||||||
},
|
},
|
||||||
"Vastai_va16": {
|
"Vastai_va16": {
|
||||||
@@ -4503,22 +4501,22 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||||
"attributableFailureCount": 8,
|
"attributableFailureCount": 9,
|
||||||
"consecutiveFailures": 8,
|
"consecutiveFailures": 9,
|
||||||
"consecutivePlatformFailures": 0,
|
"consecutivePlatformFailures": 0,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 8,
|
"decisionTotal": 9,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"framework_architecture_unsupported": 1,
|
"framework_architecture_unsupported": 1,
|
||||||
"platform_infrastructure": 1,
|
"platform_infrastructure": 1,
|
||||||
"tokenizer_compatibility": 7
|
"tokenizer_compatibility": 8
|
||||||
},
|
},
|
||||||
"failureCount": 9,
|
"failureCount": 10,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_fix_tokenizer",
|
"framework": "vllm_fix_tokenizer",
|
||||||
"lastPlatformFailureAt": "2026-09-08T18:27:21+00:00",
|
"lastPlatformFailureAt": "2026-09-08T18:27:21+00:00",
|
||||||
"lastTerminalAt": "2026-09-09T17:24:58.529069+00:00",
|
"lastTerminalAt": "2026-09-10T10:46:39.406893+00:00",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 1,
|
"platformFailureCount": 1,
|
||||||
@@ -4526,7 +4524,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Sunrise_pt-200-x1",
|
"targetGpu": "Sunrise_pt-200-x1",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 9,
|
"total": 10,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||||
@@ -4678,19 +4676,19 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"hygon_k100-ai|vllm|text-generation": {
|
"hygon_k100-ai|vllm|text-generation": {
|
||||||
"attributableFailureCount": 8,
|
"attributableFailureCount": 7,
|
||||||
"consecutiveFailures": 8,
|
"consecutiveFailures": 7,
|
||||||
"consecutivePlatformFailures": 0,
|
"consecutivePlatformFailures": 0,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 8,
|
"decisionTotal": 7,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 12,
|
"ambiguous_runtime": 12,
|
||||||
"framework_architecture_unsupported": 6,
|
"framework_architecture_unsupported": 5,
|
||||||
"model_load": 1,
|
"model_load": 1,
|
||||||
"repository_structure": 1
|
"repository_structure": 1
|
||||||
},
|
},
|
||||||
"failureCount": 20,
|
"failureCount": 19,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm",
|
"framework": "vllm",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
@@ -4702,7 +4700,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "hygon_k100-ai",
|
"targetGpu": "hygon_k100-ai",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 20,
|
"total": 19,
|
||||||
"unresolvedFailureCount": 12
|
"unresolvedFailureCount": 12
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
@@ -7053,13 +7051,13 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"terminalRecords": 1557,
|
"terminalRecords": 1558,
|
||||||
"totalRecords": 1644,
|
"totalRecords": 1645,
|
||||||
"totals": {
|
"totals": {
|
||||||
"attributableFailureCount": 405,
|
"attributableFailureCount": 406,
|
||||||
"decisionFailureRate": 0.8882,
|
"decisionFailureRate": 0.8884,
|
||||||
"decisionSuccessRate": 0.1118,
|
"decisionSuccessRate": 0.1116,
|
||||||
"decisionTotal": 456,
|
"decisionTotal": 457,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 331,
|
"ambiguous_runtime": 331,
|
||||||
"backend_operator": 34,
|
"backend_operator": 34,
|
||||||
@@ -7069,25 +7067,25 @@
|
|||||||
"platform_infrastructure": 2,
|
"platform_infrastructure": 2,
|
||||||
"repository_structure": 5,
|
"repository_structure": 5,
|
||||||
"runtime_memory": 5,
|
"runtime_memory": 5,
|
||||||
"tokenizer_compatibility": 33,
|
"tokenizer_compatibility": 34,
|
||||||
"参数/模板问题": 95,
|
"参数/模板问题": 95,
|
||||||
"验证失败": 673
|
"验证失败": 673
|
||||||
},
|
},
|
||||||
"failureCount": 1506,
|
"failureCount": 1507,
|
||||||
"failureRate": 0.9672,
|
"failureRate": 0.9673,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 2,
|
"platformFailureCount": 2,
|
||||||
"successCount": 51,
|
"successCount": 51,
|
||||||
"successRate": 0.0328,
|
"successRate": 0.0327,
|
||||||
"total": 1557,
|
"total": 1558,
|
||||||
"unresolvedFailureCount": 1099
|
"unresolvedFailureCount": 1099
|
||||||
},
|
},
|
||||||
"warnings": [
|
"warnings": [
|
||||||
"GPU Cambricon_mlu-370-x8 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 Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Ascend_910-b3 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 Iluvatar_mrv-100 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。",
|
||||||
"GPU Ascend_910-b4 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 Vastai_va16 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 MetaX_c-500 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。",
|
||||||
@@ -7095,7 +7093,7 @@
|
|||||||
"GPU hygon_k100-ai 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 Cambricon_mlu-370-x4 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 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 Iluvatar_bi-150 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 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-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 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 Biren_166m|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 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||||
@@ -7116,6 +7114,6 @@
|
|||||||
]
|
]
|
||||||
},
|
},
|
||||||
"storageMode": "decision_state_only",
|
"storageMode": "decision_state_only",
|
||||||
"summarizedRecords": 1644,
|
"summarizedRecords": 1645,
|
||||||
"version": 1
|
"version": 1
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -1,3 +1,4 @@
|
|||||||
|
{"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": "2026-09-10T10:46:39.406893+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:43:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4107002", "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": "2026-09-10T10:30:02.547307+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:27:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471919", "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": "2026-09-10T10:30:02.547307+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:27:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471919", "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": "2026-09-10T10:30:02.547284+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:23:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471918", "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": "2026-09-10T10:30:02.547284+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:23:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471918", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T10:21:30.006897+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493599", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T10:21:30.006897+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493599", "taskType": "text-generation", "verifyResult": -1}
|
||||||
@@ -297,4 +298,3 @@
|
|||||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T22:14:22.623409+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T22:07:23+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4498543", "taskType": "text-generation", "verifyResult": 1}
|
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T22:14:22.623409+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T22:07:23+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4498543", "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_moe"], "framework": "vllm", "lastSyncTime": "2026-09-07T22:14:22.623429+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T22:07:23+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4531835", "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_moe"], "framework": "vllm", "lastSyncTime": "2026-09-07T22:14:22.623429+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T22:07:23+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4531835", "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": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "llamacpp", "lastSyncTime": "2026-09-07T21:52:09.703368+00:00", "modelId": "ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T21:51:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "3987945", "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": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "llamacpp", "lastSyncTime": "2026-09-07T21:52:09.703368+00:00", "modelId": "ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T21:51:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "3987945", "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_moe"], "framework": "vllm", "lastSyncTime": "2026-09-07T21:05:55.523169+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:53:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4482387", "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
@@ -1,24 +1,24 @@
|
|||||||
{
|
{
|
||||||
"agentVersion": "2026.09.04.4",
|
"agentVersion": "2026.09.04.4",
|
||||||
"checksums": {
|
"checksums": {
|
||||||
".modelhub_state/architecture_compatibility_blacklist.json": "cb5707b708cc7c7d944273ab9bc9d7a0a971edfaa51169f0c028daea007c9827",
|
".modelhub_state/architecture_compatibility_blacklist.json": "cd15e063a88bf624c13a671a522323b37e21fe29d332c2fcafb2b07a7b9e549b",
|
||||||
".modelhub_state/architecture_history_backfill.json": "a1e0d7512c9b6511da78ccb1cee15d508347b7a35fb79476c54faf07dda65d8b",
|
".modelhub_state/architecture_history_backfill.json": "1bfc8496f80923d71011c478b0a6634b5969057996c0b6fdf08042671e8939c3",
|
||||||
".modelhub_state/market_intelligence.json": "28d764a47f81c58dab40f90b2707b445ace99895134c6c8eb3bfc601fbed4137",
|
".modelhub_state/market_intelligence.json": "99f27719d8980bdcf526423a48e1941ee405f1b761283892b5ba2550c5b96f76",
|
||||||
".modelhub_state/official_capabilities.json": "a2d1eb20ac583e38debe4a281b1dc7cda562c1ce3c40c8fcfa76c22873a25cae",
|
".modelhub_state/official_capabilities.json": "b1e5e7eea5871dd8ea2260ee45bfb199ed92485a0db589c2b66991cb9bd34b6a",
|
||||||
".modelhub_state/outcome_checkpoint.json": "a722ba47ec3aa05af0813e7deeeb8b53520f88a2038968d20c2916b625a0d52c",
|
".modelhub_state/outcome_checkpoint.json": "586229a1f964c9f33fa6f0f3e2532cfc92009f7187da06bb115109780814aa46",
|
||||||
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
|
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
|
||||||
".modelhub_state/recent_outcomes.jsonl": "a47e8ee12281bdf186a48cc5b0b5f4ad589c7369be624c3a5c48913f3ade1f06",
|
".modelhub_state/recent_outcomes.jsonl": "2bffda803018c0501d2f98b450cf20df3714d4246604cc966dfe3fd14b70ef18",
|
||||||
".modelhub_state/recovery_active_tasks.jsonl": "fda41ad421d0d3f7e02616078c2c1f4f080022335d6c31230cc98f48a4dce79d",
|
".modelhub_state/recovery_active_tasks.jsonl": "cadb08cd5c26b26311c49598a2655a0b34a21a1171d81ab03ed9135a098d2478",
|
||||||
".modelhub_state/recovery_intents.jsonl": "ce02d188e8328d579f281633b2a3142fade7d508d76ff61702a0a936958409d7",
|
".modelhub_state/recovery_intents.jsonl": "968749fffb04820a94d2cf2c7c14a8a4e65f2ecfbd8dbf0dbf960eb9f95ee7b5",
|
||||||
".modelhub_state/routing_intelligence.json": "f36cfaf9f9ff191164b0ce0a73a3ce4bbc3a2dc4589f252d583e33b427807fc0",
|
".modelhub_state/routing_intelligence.json": "f36cfaf9f9ff191164b0ce0a73a3ce4bbc3a2dc4589f252d583e33b427807fc0",
|
||||||
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
|
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
|
||||||
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
|
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
|
||||||
"ledger/submissions.jsonl": "76cbabbced897a94b01593ff4cb86c58b9b0394b6c8fa89dd11a295e4678f70f",
|
"ledger/submissions.jsonl": "76cbabbced897a94b01593ff4cb86c58b9b0394b6c8fa89dd11a295e4678f70f",
|
||||||
"outcomes/submissions.jsonl": "7e7dceeb82e33a52f232d56ceba319292e0b24b25bc8ec08e03fa95367ce1163"
|
"outcomes/submissions.jsonl": "7e7dceeb82e33a52f232d56ceba319292e0b24b25bc8ec08e03fa95367ce1163"
|
||||||
},
|
},
|
||||||
"generation": 5124,
|
"generation": 5125,
|
||||||
"phase": "cycle",
|
"phase": "cycle",
|
||||||
"schemaVersion": 1,
|
"schemaVersion": 1,
|
||||||
"updatedAt": "2026-09-10T10:45:38.815082+00:00",
|
"updatedAt": "2026-09-10T10:50:21.573195+00:00",
|
||||||
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
|
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
|
||||||
}
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user