state: generation 17050 (cycle)
This commit is contained in:
@@ -3261,7 +3261,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-27T04:26:29.464266+00:00",
|
||||
"generatedAt": "2026-09-27T04:31:49.161682+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 164,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -396,99 +396,99 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-27T04:30:44.347560+00:00",
|
||||
"generatedAt": "2026-09-27T04:32:28.975690+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1268.4888888888888,
|
||||
"backlogHours": 1278.044776119403,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.1300526415853243,
|
||||
"queueFactor": 0.9242004792562082,
|
||||
"queueWeight": 0.9242004792562082,
|
||||
"recentSuccess": 55,
|
||||
"recentSuccessRate": 0.4074074074074074,
|
||||
"recentTerminal": 135,
|
||||
"recentWilsonLowerBound": 0.3281978223373858,
|
||||
"qualityFactor": 0.9105430190304553,
|
||||
"queueFactor": 0.916021346431558,
|
||||
"queueWeight": 0.916021346431558,
|
||||
"recentSuccess": 52,
|
||||
"recentSuccessRate": 0.3880597014925373,
|
||||
"recentTerminal": 134,
|
||||
"recentWilsonLowerBound": 0.30976736607385463,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.0443951929379007,
|
||||
"selectionWeight": 0.8340768422761334,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 22.5,
|
||||
"waiting": 28541
|
||||
"throughputPerHour": 22.333333333333332,
|
||||
"waiting": 28543
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 145.22155688622755,
|
||||
"backlogHours": 137.89772727272728,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.10941191920023775,
|
||||
"queueFactor": 1.27924735075308,
|
||||
"queueWeight": 1.27924735075308,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.16167664670658682,
|
||||
"recentTerminal": 167,
|
||||
"recentWilsonLowerBound": 0.11355627347059115,
|
||||
"qualityFactor": 0.09792511904194513,
|
||||
"queueFactor": 1.2792456194605184,
|
||||
"queueWeight": 1.2792456194605184,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.1590909090909091,
|
||||
"recentTerminal": 176,
|
||||
"recentWilsonLowerBound": 0.11242190844886836,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.1399649077777142,
|
||||
"selectionWeight": 0.1252702795695581,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 27.833333333333332,
|
||||
"waiting": 4042
|
||||
"throughputPerHour": 29.333333333333332,
|
||||
"waiting": 4045
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1278.0845070422536,
|
||||
"backlogHours": 1296.1714285714286,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.29603765172502783,
|
||||
"queueFactor": 0.9231563342526629,
|
||||
"queueWeight": 0.9231563342526629,
|
||||
"qualityFactor": 0.27986049916838557,
|
||||
"queueFactor": 0.914088274708377,
|
||||
"queueWeight": 0.914088274708377,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.2676056338028169,
|
||||
"recentTerminal": 71,
|
||||
"recentWilsonLowerBound": 0.17852666541700804,
|
||||
"recentSuccessRate": 0.2714285714285714,
|
||||
"recentTerminal": 70,
|
||||
"recentWilsonLowerBound": 0.18119460808784751,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.2732890333672432,
|
||||
"selectionWeight": 0.25581720084385473,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.833333333333334,
|
||||
"waiting": 15124
|
||||
"throughputPerHour": 11.666666666666666,
|
||||
"waiting": 15122
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 457.4086956521739,
|
||||
"backlogHours": 449.64102564102564,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.16568736173292664,
|
||||
"queueFactor": 1.076994603098987,
|
||||
"queueWeight": 1.076994603098987,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.2,
|
||||
"recentTerminal": 115,
|
||||
"recentWilsonLowerBound": 0.1371296827840679,
|
||||
"qualityFactor": 0.2238973092682124,
|
||||
"queueFactor": 1.0714147360718418,
|
||||
"queueWeight": 1.0714147360718418,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.23076923076923078,
|
||||
"recentTerminal": 117,
|
||||
"recentWilsonLowerBound": 0.1637205217381598,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.1784443943880716,
|
||||
"selectionWeight": 0.23988687651679733,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 19.166666666666668,
|
||||
"waiting": 8767
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.5,
|
||||
"waiting": 8768
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 41.8523076923077,
|
||||
"backlogHours": 42.148606811145505,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -498,37 +498,37 @@
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.043076923076923075,
|
||||
"recentTerminal": 325,
|
||||
"recentWilsonLowerBound": 0.02583052919996028,
|
||||
"running": 25,
|
||||
"recentSuccessRate": 0.043343653250773995,
|
||||
"recentTerminal": 323,
|
||||
"recentWilsonLowerBound": 0.025991545809751486,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 54.166666666666664,
|
||||
"waiting": 2267
|
||||
"throughputPerHour": 53.833333333333336,
|
||||
"waiting": 2269
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 97.45945945945945,
|
||||
"backlogHours": 96.52173913043478,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.12033425578789482,
|
||||
"qualityFactor": 0.10764648047141717,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 46,
|
||||
"recentSuccessRate": 0.1554054054054054,
|
||||
"recentTerminal": 296,
|
||||
"recentWilsonLowerBound": 0.11857552588720112,
|
||||
"running": 11,
|
||||
"selectionWeight": 0.15643453252426326,
|
||||
"recentSuccessRate": 0.15384615384615385,
|
||||
"recentTerminal": 299,
|
||||
"recentWilsonLowerBound": 0.11736412757816764,
|
||||
"running": 10,
|
||||
"selectionWeight": 0.13994042461284234,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 49.333333333333336,
|
||||
"waiting": 4808
|
||||
"throughputPerHour": 49.833333333333336,
|
||||
"waiting": 4810
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
@@ -538,15 +538,15 @@
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.6037693492820245,
|
||||
"queueFactor": 0.8160714336500631,
|
||||
"queueWeight": 0.8160714336500631,
|
||||
"qualityFactor": 0.5524499350511144,
|
||||
"queueFactor": 0.8097603189416718,
|
||||
"queueWeight": 0.8097603189416718,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.3939393939393939,
|
||||
"recentTerminal": 33,
|
||||
"recentWilsonLowerBound": 0.24682882231508205,
|
||||
"running": 3,
|
||||
"selectionWeight": 0.49271891846254745,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.44735203560629627,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 5.5,
|
||||
@@ -554,47 +554,47 @@
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 383.96,
|
||||
"backlogHours": 391.59183673469386,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.2006195412696179,
|
||||
"queueFactor": 1.1056464913181476,
|
||||
"queueWeight": 1.1056464913181476,
|
||||
"qualityFactor": 0.19216048693297946,
|
||||
"queueFactor": 1.093861810568073,
|
||||
"queueWeight": 1.093861810568073,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.20666666666666667,
|
||||
"recentTerminal": 150,
|
||||
"recentWilsonLowerBound": 0.14958803521394032,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.22181429189460936,
|
||||
"recentSuccessRate": 0.2108843537414966,
|
||||
"recentTerminal": 147,
|
||||
"recentWilsonLowerBound": 0.1527313597425877,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.21019701815615147,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 25.0,
|
||||
"waiting": 9599
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 24.5,
|
||||
"waiting": 9594
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 587.7222222222222,
|
||||
"backlogHours": 552.0521739130435,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.35522778031249136,
|
||||
"queueFactor": 1.0372498309128313,
|
||||
"queueWeight": 1.0372498309128313,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.26851851851851855,
|
||||
"recentTerminal": 108,
|
||||
"recentWilsonLowerBound": 0.19394781819614243,
|
||||
"qualityFactor": 0.3653622504726742,
|
||||
"queueFactor": 1.038940045054849,
|
||||
"queueWeight": 1.038940045054849,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.2782608695652174,
|
||||
"recentTerminal": 115,
|
||||
"recentWilsonLowerBound": 0.20453775426690435,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.36845995506467205,
|
||||
"selectionWeight": 0.3795894729674211,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.0,
|
||||
"waiting": 10579
|
||||
"throughputPerHour": 19.166666666666668,
|
||||
"waiting": 10581
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
@@ -605,14 +605,14 @@
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8353990091998449,
|
||||
"queueWeight": 0.8353990091998449,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.6078431372549019,
|
||||
"queueFactor": 0.8289384240636208,
|
||||
"queueWeight": 0.8289384240636208,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.6274509803921569,
|
||||
"recentTerminal": 51,
|
||||
"recentWilsonLowerBound": 0.4708491122516505,
|
||||
"recentWilsonLowerBound": 0.4902496270033425,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.0884975229996123,
|
||||
"selectionWeight": 2.072346060159052,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 8.5,
|
||||
@@ -620,74 +620,74 @@
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 4296.521739130435,
|
||||
"backlogHours": 4296.782608695652,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.4761464510502999,
|
||||
"queueFactor": 0.7696471002990742,
|
||||
"queueWeight": 0.7696471002990742,
|
||||
"qualityFactor": 0.43567477592289267,
|
||||
"queueFactor": 0.7636880545823024,
|
||||
"queueWeight": 0.7636880545823024,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.391304347826087,
|
||||
"recentTerminal": 23,
|
||||
"recentWilsonLowerBound": 0.22157377982382145,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.3664647353685584,
|
||||
"selectionWeight": 0.3327196220551344,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 3.8333333333333335,
|
||||
"waiting": 16470
|
||||
"waiting": 16471
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 750.0,
|
||||
"backlogHours": 712.1694915254237,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.3900791917330431,
|
||||
"qualityFactor": 0.316761549147081,
|
||||
"queueFactor": 1.0,
|
||||
"queueWeight": 1.0,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.2767857142857143,
|
||||
"recentTerminal": 112,
|
||||
"recentWilsonLowerBound": 0.2023765976068205,
|
||||
"recentSuccessRate": 0.2627118644067797,
|
||||
"recentTerminal": 118,
|
||||
"recentWilsonLowerBound": 0.19168832306387246,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.3900791917330431,
|
||||
"selectionWeight": 0.316761549147081,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.666666666666668,
|
||||
"waiting": 14000
|
||||
"throughputPerHour": 19.666666666666668,
|
||||
"waiting": 14006
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 754.9640287769784,
|
||||
"backlogHours": 771.7058823529411,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.14974259027165476,
|
||||
"queueFactor": 0.999010954791002,
|
||||
"queueWeight": 0.999010954791002,
|
||||
"qualityFactor": 0.14394297967333758,
|
||||
"queueFactor": 0.9880290938442563,
|
||||
"queueWeight": 0.9880290938442563,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.18705035971223022,
|
||||
"recentTerminal": 139,
|
||||
"recentWilsonLowerBound": 0.13096550054880465,
|
||||
"recentSuccessRate": 0.19117647058823528,
|
||||
"recentTerminal": 136,
|
||||
"recentWilsonLowerBound": 0.1339352099342089,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.14959448808016362,
|
||||
"selectionWeight": 0.14221985177188992,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 23.166666666666668,
|
||||
"waiting": 17490
|
||||
"throughputPerHour": 22.666666666666668,
|
||||
"waiting": 17492
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-27T04:21:40.500995+00:00",
|
||||
"queueAttemptedAt": "2026-09-27T04:32:28.975690+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-27T04:21:40.500995+00:00",
|
||||
"queueUpdatedAt": "2026-09-27T04:32:28.975690+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Cambricon_mlu-370-x4",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-26T23:17:47.128061+00:00",
|
||||
"lastSyncTime": "2026-09-26T23:17:46.651661+00:00",
|
||||
"generatedAt": "2026-09-27T04:31:49.086558+00:00",
|
||||
"lastSyncTime": "2026-09-27T04:31:48.760568+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3571,13 +3571,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 25,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 96,
|
||||
"ambiguous_runtime": 97,
|
||||
"framework_architecture_unsupported": 24,
|
||||
"platform_infrastructure": 1,
|
||||
"repository_structure": 1,
|
||||
"参数/模板问题": 6
|
||||
},
|
||||
"failureCount": 128,
|
||||
"failureCount": 129,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
@@ -3587,8 +3587,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 128,
|
||||
"unresolvedFailureCount": 102
|
||||
"total": 129,
|
||||
"unresolvedFailureCount": 103
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
"attributableFailureCount": 204,
|
||||
@@ -6111,7 +6111,7 @@
|
||||
"decisionSuccessRate": 0.0657,
|
||||
"decisionTotal": 137,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 167,
|
||||
"ambiguous_runtime": 168,
|
||||
"backend_operator": 15,
|
||||
"context_length": 4,
|
||||
"framework_architecture_unsupported": 76,
|
||||
@@ -6123,18 +6123,18 @@
|
||||
"tokenizer_compatibility": 2,
|
||||
"参数/模板问题": 29
|
||||
},
|
||||
"failureCount": 326,
|
||||
"failureRate": 0.9731,
|
||||
"failureCount": 327,
|
||||
"failureRate": 0.9732,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 9,
|
||||
"successRate": 0.0269,
|
||||
"total": 335,
|
||||
"unresolvedFailureCount": 196
|
||||
"successRate": 0.0268,
|
||||
"total": 336,
|
||||
"unresolvedFailureCount": 197
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-26T23:17:47.116306+00:00",
|
||||
"generatedAt": "2026-09-27T04:31:49.074572+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6168,7 +6168,7 @@
|
||||
"decisionSuccessRate": 0.1654,
|
||||
"decisionTotal": 387,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 246,
|
||||
"ambiguous_runtime": 247,
|
||||
"context_length": 1,
|
||||
"framework_architecture_unsupported": 179,
|
||||
"memory_capacity": 19,
|
||||
@@ -6180,15 +6180,15 @@
|
||||
"日志缺失": 14,
|
||||
"验证失败": 175
|
||||
},
|
||||
"failureCount": 1029,
|
||||
"failureRate": 0.9414,
|
||||
"failureCount": 1030,
|
||||
"failureRate": 0.9415,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 64,
|
||||
"successRate": 0.0586,
|
||||
"total": 1093,
|
||||
"unresolvedFailureCount": 703
|
||||
"successRate": 0.0585,
|
||||
"total": 1094,
|
||||
"unresolvedFailureCount": 704
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 187,
|
||||
@@ -7906,6 +7906,29 @@
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gpt_oss|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "gpt_oss",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2_moe|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -22691,13 +22714,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 16
|
||||
"ambiguous_runtime": 17
|
||||
},
|
||||
"failureCount": 16,
|
||||
"failureCount": 17,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-23T02:06:44.350356+00:00",
|
||||
"lastTerminalAt": "2026-09-27T04:31:48.760568+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -22705,8 +22728,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 16
|
||||
"total": 17,
|
||||
"unresolvedFailureCount": 17
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -22844,10 +22867,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"ambiguous_runtime": 6,
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 8,
|
||||
"failureCount": 7,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -22859,8 +22882,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 7
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -23463,6 +23486,31 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gpt_oss|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastTerminalAt": "2026-09-27T04:31:48.760568+00:00",
|
||||
"modelType": "gpt_oss",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -23895,9 +23943,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3
|
||||
"ambiguous_runtime": 2
|
||||
},
|
||||
"failureCount": 3,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastTerminalAt": "2026-09-26T07:10:36.169068+00:00",
|
||||
@@ -23910,8 +23958,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation|mpt|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -28445,6 +28493,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gpt_oss|none|33": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "gpt_oss",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2_moe|none|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -51099,15 +51171,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17054,
|
||||
"totalRecords": 17275,
|
||||
"terminalRecords": 17055,
|
||||
"totalRecords": 17276,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6114,
|
||||
"decisionFailureRate": 0.8636,
|
||||
"decisionSuccessRate": 0.1364,
|
||||
"decisionTotal": 7080,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4413,
|
||||
"ambiguous_runtime": 4414,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
@@ -51123,72 +51195,72 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16088,
|
||||
"failureCount": 16089,
|
||||
"failureRate": 0.9434,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 938,
|
||||
"successCount": 966,
|
||||
"successRate": 0.0566,
|
||||
"total": 17054,
|
||||
"unresolvedFailureCount": 9036
|
||||
"total": 17055,
|
||||
"unresolvedFailureCount": 9037
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Biren_166m 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-100 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 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 Kunlunxin_p-800 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-b4 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 MetaX_c-500 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 Vastai_va16 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 Ascend_910-b3 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 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Kunlunxin_p-800 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 Ascend_910-b3|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-100|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。",
|
||||
"组合 Cambricon_mlu-370-x4|vllm-mlu|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_tokenizer_patch|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-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|vllm_fix_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 Sunrise_pt-200-x1|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 Sunrise_pt-200-x1|vllm_fix_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 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 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 Ascend_910-b4|llamacpp|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_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 MetaX_c-500|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 hygon_k100-ai|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Vastai_va16|vllm_fix_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 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 Iluvatar_bi-150|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x4|vllm-mlu|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|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|vllm_fix_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 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 MetaX_c-500|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Sunrise_pt-200-x1|vllm_fix_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 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"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 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 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x4|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 MetaX_c-500|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Biren_166m|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 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Vastai_va16|vllm_fix_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 Iluvatar_mrv-100|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 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|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-100|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 Sunrise_pt-200-x1|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 Sunrise_pt-200-x1|vllm|visual-multi-modal 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。",
|
||||
"组合 Biren_166m|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 Cambricon_mlu-370-x8|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 MetaX_c-500|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
"组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17275,
|
||||
"summarizedRecords": 17276,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -2,6 +2,7 @@
|
||||
{"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": "2026-09-26T17:57:36.159288+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-26T17:52:08+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457999", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-26T17:14:27.552028+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-26T17:12:10+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458906", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-26T22:23:08.761596+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "failed", "status": "success", "submitTime": "2026-09-26T08:18:32.495861+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5097281", "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_tokenizer_patch", "lastSyncTime": "2026-09-27T04:31:48.760568+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "failed", "status": "success", "submitTime": "2026-09-26T08:01:50.847636+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5097139", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-09-26T21:44:28.758538+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-24T19:41:33.877071+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5067517", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-24T03:51:15.462039+00:00", "modelId": "BAAI/CareBot_Medical_multi-llama3-8b-rl", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-24T03:50:10+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457984", "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": "2026-09-24T02:15:32.962539+00:00", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-24T02:14:08+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457989", "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": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-25T09:35:33.057138+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124576, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124576}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:10:00.705684+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991871", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-24T20:32:32.162698+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3403624536, "estimatedRequiredGiB": 3.828, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 3425449433, "modelscopeLicense": "llama2", "modelscopeParams": 3204165888, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3425449433}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:10:00.601936+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991870", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-24T05:11:42.061432+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096479058, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096479058}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:10:00.507387+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991869", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-23T14:22:36.780059+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093203965, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm", "custom_tag:quantized", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093203965}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:49.393439+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991868", "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
Reference in New Issue
Block a user