CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 16859 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-26 22:40:12 +00:00
parent ec09b92641
commit 7284e47c2a
8 changed files with 1625 additions and 1626 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -3261,7 +3261,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-26T22:34:20.763788+00:00", "generatedAt": "2026-09-26T22:39:20.871919+00:00",
"summary": { "summary": {
"activeBlockCount": 164, "activeBlockCount": 164,
"byGpuFramework": { "byGpuFramework": {

250
.modelhub_state/market_intelligence.json
View File

@@ -396,99 +396,99 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-26T22:38:18.053962+00:00", "generatedAt": "2026-09-26T22:40:05.166696+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1299.2727272727273, "backlogHours": 1309.0992366412215,
"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": 2.2750217299546884, "qualityFactor": 2.217205649766655,
"queueFactor": 0.9333439280771803, "queueFactor": 0.9309419668252304,
"queueWeight": 0.9333439280771803, "queueWeight": 0.9309419668252304,
"recentSuccess": 50, "recentSuccess": 51,
"recentSuccessRate": 0.3787878787878788, "recentSuccessRate": 0.3893129770992366,
"recentTerminal": 132, "recentTerminal": 131,
"recentWilsonLowerBound": 0.30056865609414096, "recentWilsonLowerBound": 0.3101054456646504,
"running": 8, "running": 8,
"selectionWeight": 2.123377717896851, "selectionWeight": 2.064089788449783,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.0, "throughputPerHour": 21.833333333333332,
"waiting": 28584 "waiting": 28582
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 121.05527638190955, "backlogHours": 122.84693877551021,
"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": 0.4702749374697578, "qualityFactor": 0.4726720881576659,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 39, "recentSuccess": 40,
"recentSuccessRate": 0.19597989949748743, "recentSuccessRate": 0.20408163265306123,
"recentTerminal": 199, "recentTerminal": 196,
"recentWilsonLowerBound": 0.14680692645920698, "recentWilsonLowerBound": 0.1536022459546319,
"running": 8, "running": 8,
"selectionWeight": 0.6113574187106852, "selectionWeight": 0.6144737146049657,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": true,
"throughputPerHour": 33.166666666666664, "throughputPerHour": 32.666666666666664,
"waiting": 4015 "waiting": 4013
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1178.025974025974, "backlogHours": 1177.7922077922078,
"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": 0.25681054447518664, "qualityFactor": 0.23366234544234812,
"queueFactor": 0.9471603839801402, "queueFactor": 0.9458193454107809,
"queueWeight": 0.9471603839801402, "queueWeight": 0.9458193454107809,
"recentSuccess": 14, "recentSuccess": 14,
"recentSuccessRate": 0.18181818181818182, "recentSuccessRate": 0.18181818181818182,
"recentTerminal": 77, "recentTerminal": 77,
"recentWilsonLowerBound": 0.1115115201004776, "recentWilsonLowerBound": 0.1115115201004776,
"running": 7, "running": 7,
"selectionWeight": 0.24324077391526666, "selectionWeight": 0.22100236661342948,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 12.833333333333334, "throughputPerHour": 12.833333333333334,
"waiting": 15118 "waiting": 15115
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 441.22689075630257, "backlogHours": 434.0330578512396,
"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": 0.4199211925464142, "qualityFactor": 0.41037877295261893,
"queueFactor": 1.097482133664799, "queueFactor": 1.0986012096628528,
"queueWeight": 1.097482133664799, "queueWeight": 1.0986012096628528,
"recentSuccess": 24, "recentSuccess": 25,
"recentSuccessRate": 0.20168067226890757, "recentSuccessRate": 0.2066115702479339,
"recentTerminal": 119, "recentTerminal": 121,
"recentWilsonLowerBound": 0.13944089576973434, "recentWilsonLowerBound": 0.14404553713266344,
"running": 8, "running": 7,
"selectionWeight": 0.46085600636690555, "selectionWeight": 0.4508426163857044,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 19.833333333333332, "throughputPerHour": 20.166666666666668,
"waiting": 8751 "waiting": 8753
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 43.12048192771084, "backlogHours": 43.102409638554214,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -501,193 +501,193 @@
"recentSuccessRate": 0.02710843373493976, "recentSuccessRate": 0.02710843373493976,
"recentTerminal": 332, "recentTerminal": 332,
"recentWilsonLowerBound": 0.014325946775155833, "recentWilsonLowerBound": 0.014325946775155833,
"running": 25, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 55.333333333333336, "throughputPerHour": 55.333333333333336,
"waiting": 2386 "waiting": 2385
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 140.4927536231884, "backlogHours": 140.3768115942029,
"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": 0.4894051591824525, "qualityFactor": 0.41788743493193276,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 41, "recentSuccess": 40,
"recentSuccessRate": 0.19806763285024154, "recentSuccessRate": 0.1932367149758454,
"recentTerminal": 207, "recentTerminal": 207,
"recentWilsonLowerBound": 0.14949193994068544, "recentWilsonLowerBound": 0.14523760917281775,
"running": 9, "running": 10,
"selectionWeight": 0.6362267069371882, "selectionWeight": 0.5432536654115127,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 34.5, "throughputPerHour": 34.5,
"waiting": 4847 "waiting": 4843
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2592.162162162162, "backlogHours": 2524.263157894737,
"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": 1.1251918782114285, "qualityFactor": 1.1915361283994736,
"queueFactor": 0.8414870364147196, "queueFactor": 0.8436227830186878,
"queueWeight": 0.8414870364147196, "queueWeight": 0.8436227830186878,
"recentSuccess": 13, "recentSuccess": 14,
"recentSuccessRate": 0.35135135135135137, "recentSuccessRate": 0.3684210526315789,
"recentTerminal": 37, "recentTerminal": 38,
"recentWilsonLowerBound": 0.21825406631100872, "recentWilsonLowerBound": 0.23384013155413794,
"running": 2, "running": 2,
"selectionWeight": 0.9468343789940471, "selectionWeight": 1.0052070247076765,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.166666666666667, "throughputPerHour": 6.333333333333333,
"waiting": 15985 "waiting": 15987
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 368.11538461538464, "backlogHours": 361.0943396226415,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Kunlunxin_p-800", "gpu": "Kunlunxin_p-800",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.9886434438069922, "qualityFactor": 0.8093474150128571,
"queueFactor": 1.1277144871242093, "queueFactor": 1.12934177195299,
"queueWeight": 1.1277144871242093, "queueWeight": 1.12934177195299,
"recentSuccess": 42, "recentSuccess": 41,
"recentSuccessRate": 0.2692307692307692, "recentSuccessRate": 0.2578616352201258,
"recentTerminal": 156, "recentTerminal": 159,
"recentWilsonLowerBound": 0.205789325979125, "recentWilsonLowerBound": 0.1961408407413688,
"running": 8, "running": 10,
"selectionWeight": 1.1149075341815142, "selectionWeight": 0.914029843796192,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 26.0, "throughputPerHour": 26.5,
"waiting": 9571 "waiting": 9569
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 681.8709677419355, "backlogHours": 689.1521739130435,
"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": 1.5906679431502548, "qualityFactor": 1.3637059549422794,
"queueFactor": 1.0281143594521425, "queueFactor": 1.0249937673443532,
"queueWeight": 1.0281143594521425, "queueWeight": 1.0249937673443532,
"recentSuccess": 32, "recentSuccess": 31,
"recentSuccessRate": 0.34408602150537637, "recentSuccessRate": 0.33695652173913043,
"recentTerminal": 93, "recentTerminal": 92,
"recentWilsonLowerBound": 0.25544922494036565, "recentWilsonLowerBound": 0.24863459523567621,
"running": 4, "running": 4,
"selectionWeight": 1.6353885534729813, "selectionWeight": 1.3977901043062158,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.5, "throughputPerHour": 15.333333333333334,
"waiting": 10569 "waiting": 10567
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2306.072727272727, "backlogHours": 2186.896551724138,
"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": 2.5, "qualityFactor": 2.5,
"queueFactor": 0.856378597449679, "queueFactor": 0.8619741824761981,
"queueWeight": 0.856378597449679, "queueWeight": 0.8619741824761981,
"recentSuccess": 24, "recentSuccess": 26,
"recentSuccessRate": 0.43636363636363634, "recentSuccessRate": 0.4482758620689655,
"recentTerminal": 55, "recentTerminal": 58,
"recentWilsonLowerBound": 0.31373238636001305, "recentWilsonLowerBound": 0.32749651292941145,
"running": 5, "running": 4,
"selectionWeight": 2.1409464936241975, "selectionWeight": 2.154935456190495,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 9.166666666666666, "throughputPerHour": 9.666666666666666,
"waiting": 21139 "waiting": 21140
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 2900.470588235294, "backlogHours": 2900.8235294117644,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Sunrise_pt-200-x1", "gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.32649113283785475, "qualityFactor": 0.2970621164365528,
"queueFactor": 0.8274208968086899, "queueFactor": 0.8262097157945751,
"queueWeight": 0.8274208968086899, "queueWeight": 0.8262097157945751,
"recentSuccess": 8, "recentSuccess": 8,
"recentSuccessRate": 0.23529411764705882, "recentSuccessRate": 0.23529411764705882,
"recentTerminal": 34, "recentTerminal": 34,
"recentWilsonLowerBound": 0.12436838109244344, "recentWilsonLowerBound": 0.12436838109244344,
"running": 2, "running": 2,
"selectionWeight": 0.2701455859327829, "selectionWeight": 0.24543560679437926,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 5.666666666666667, "throughputPerHour": 5.666666666666667,
"waiting": 16436 "waiting": 16438
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 820.3106796116505, "backlogHours": 828.3529411764706,
"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": 0.7995181930806452, "qualityFactor": 0.743877620613173,
"queueFactor": 1.0, "queueFactor": 0.997094180162845,
"queueWeight": 1.0, "queueWeight": 0.997094180162845,
"recentSuccess": 27, "recentSuccess": 27,
"recentSuccessRate": 0.2621359223300971, "recentSuccessRate": 0.2647058823529412,
"recentTerminal": 103, "recentTerminal": 102,
"recentWilsonLowerBound": 0.18685666753807448, "recentWilsonLowerBound": 0.188762815237447,
"running": 16, "running": 16,
"selectionWeight": 0.7995181930806452, "selectionWeight": 0.7417160462667796,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.166666666666668, "throughputPerHour": 17.0,
"waiting": 14082 "waiting": 14082
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 845.2682926829268, "backlogHours": 812.4375,
"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": 0.644933126330445, "qualityFactor": 0.488396796431877,
"queueFactor": 0.9955144497127546, "queueFactor": 1.0,
"queueWeight": 0.9955144497127546, "queueWeight": 1.0,
"recentSuccess": 29, "recentSuccess": 28,
"recentSuccessRate": 0.23577235772357724, "recentSuccessRate": 0.21875,
"recentTerminal": 123, "recentTerminal": 128,
"recentWilsonLowerBound": 0.169470182254119, "recentWilsonLowerBound": 0.1559042491230976,
"running": 8, "running": 6,
"selectionWeight": 0.6420402463603794, "selectionWeight": 0.488396796431877,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.5, "throughputPerHour": 21.333333333333332,
"waiting": 17328 "waiting": 17332
} }
}, },
"queueAttemptedAt": "2026-09-26T22:29:50.581316+00:00", "queueAttemptedAt": "2026-09-26T22:40:05.166696+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-26T22:29:50.581316+00:00", "queueUpdatedAt": "2026-09-26T22:40:05.166696+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{ {
"catalogUpdatedAt": "2026-09-26T22:38:18.053962+00:00", "catalogUpdatedAt": "2026-09-26T22:40:05.166696+00:00",
"configuredTaskTypes": [ "configuredTaskTypes": [
"text-generation" "text-generation"
], ],
@@ -56,7 +56,7 @@
"time-series-forecasting" "time-series-forecasting"
], ],
"errors": [], "errors": [],
"generatedAt": "2026-09-26T22:38:18.053962+00:00", "generatedAt": "2026-09-26T22:40:05.166696+00:00",
"gpuCatalog": { "gpuCatalog": {
"Ascend_910-b3": { "Ascend_910-b3": {
"canVerify": true, "canVerify": true,
@@ -6265,6 +6265,6 @@
"updateTime": "2025-12-22 08:59:53" "updateTime": "2025-12-22 08:59:53"
} }
], ],
"taskTreeUpdatedAt": "2026-09-26T22:38:18.053962+00:00", "taskTreeUpdatedAt": "2026-09-26T22:40:05.166696+00:00",
"version": 1 "version": 1
} }

74
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-26T22:23:09.017195+00:00", "generatedAt": "2026-09-26T22:39:20.797015+00:00",
"lastSyncTime": "2026-09-26T22:23:08.761596+00:00", "lastSyncTime": "2026-09-26T22:39:20.440941+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -3871,12 +3871,12 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 24, "decisionTotal": 24,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 37, "ambiguous_runtime": 38,
"framework_architecture_unsupported": 23, "framework_architecture_unsupported": 23,
"memory_capacity": 1, "memory_capacity": 1,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 62, "failureCount": 63,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -3886,8 +3886,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 62, "total": 63,
"unresolvedFailureCount": 38 "unresolvedFailureCount": 39
}, },
"Cambricon_mlu-370-x8|unknown|feature_emb": { "Cambricon_mlu-370-x8|unknown|feature_emb": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -5962,7 +5962,7 @@
"decisionSuccessRate": 0.0261, "decisionSuccessRate": 0.0261,
"decisionTotal": 3720, "decisionTotal": 3720,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1577, "ambiguous_runtime": 1578,
"architecture_compatibility": 112, "architecture_compatibility": 112,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 93, "backend_operator": 93,
@@ -5976,15 +5976,15 @@
"tokenizer_compatibility": 416, "tokenizer_compatibility": 416,
"参数/模板问题": 50 "参数/模板问题": 50
}, },
"failureCount": 6120, "failureCount": 6121,
"failureRate": 0.9844, "failureRate": 0.9844,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 870, "platformFailureCount": 870,
"successCount": 97, "successCount": 97,
"successRate": 0.0156, "successRate": 0.0156,
"total": 6217, "total": 6218,
"unresolvedFailureCount": 1627 "unresolvedFailureCount": 1628
}, },
"vllm-customized": { "vllm-customized": {
"attributableFailureCount": 13, "attributableFailureCount": 13,
@@ -6134,7 +6134,7 @@
"unresolvedFailureCount": 196 "unresolvedFailureCount": 196
} }
}, },
"generatedAt": "2026-09-26T22:23:09.005096+00:00", "generatedAt": "2026-09-26T22:39:20.785156+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 102, "attributableFailureCount": 102,
@@ -6226,7 +6226,7 @@
"decisionSuccessRate": 0.0894, "decisionSuccessRate": 0.0894,
"decisionTotal": 817, "decisionTotal": 817,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 492, "ambiguous_runtime": 493,
"architecture_compatibility": 53, "architecture_compatibility": 53,
"context_length": 48, "context_length": 48,
"framework_architecture_unsupported": 297, "framework_architecture_unsupported": 297,
@@ -6239,15 +6239,15 @@
"日志缺失": 13, "日志缺失": 13,
"验证失败": 42 "验证失败": 42
}, },
"failureCount": 1594, "failureCount": 1595,
"failureRate": 0.9562, "failureRate": 0.9562,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 16, "platformFailureCount": 16,
"successCount": 73, "successCount": 73,
"successRate": 0.0438, "successRate": 0.0438,
"total": 1667, "total": 1668,
"unresolvedFailureCount": 834 "unresolvedFailureCount": 835
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"attributableFailureCount": 60, "attributableFailureCount": 60,
@@ -11711,9 +11711,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 8 "ambiguous_runtime": 9
}, },
"failureCount": 8, "failureCount": 9,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"modelType": "starcoder2", "modelType": "starcoder2",
@@ -11725,8 +11725,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 8, "total": 9,
"unresolvedFailureCount": 8 "unresolvedFailureCount": 9
}, },
"Cambricon_mlu-370-x8|vllm-customized|text-generation|aquila3|none": { "Cambricon_mlu-370-x8|vllm-customized|text-generation|aquila3|none": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -34609,9 +34609,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1 "ambiguous_runtime": 2
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"loadSizeLog2Bucket": 33, "loadSizeLog2Bucket": 33,
@@ -34624,8 +34624,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 2
}, },
"Cambricon_mlu-370-x4|vllm|text-generation|starcoder2|compressed-tensors|34": { "Cambricon_mlu-370-x4|vllm|text-generation|starcoder2|compressed-tensors|34": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -51052,15 +51052,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17052, "terminalRecords": 17053,
"totalRecords": 17273, "totalRecords": 17274,
"totals": { "totals": {
"attributableFailureCount": 6114, "attributableFailureCount": 6114,
"decisionFailureRate": 0.8636, "decisionFailureRate": 0.8636,
"decisionSuccessRate": 0.1364, "decisionSuccessRate": 0.1364,
"decisionTotal": 7080, "decisionTotal": 7080,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4412, "ambiguous_runtime": 4413,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 128, "backend_operator": 128,
@@ -51076,30 +51076,30 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16086, "failureCount": 16087,
"failureRate": 0.9433, "failureRate": 0.9434,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 937, "platformFailureCount": 937,
"successCount": 966, "successCount": 966,
"successRate": 0.0567, "successRate": 0.0566,
"total": 17052, "total": 17053,
"unresolvedFailureCount": 9035 "unresolvedFailureCount": 9036
}, },
"warnings": [ "warnings": [
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_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-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 Iluvatar_bi-150 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 Kunlunxin_p-800 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-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU 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 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 Ascend_910-b3 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 Iluvatar_bi-150 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 Sunrise_pt-200-x1 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 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。", "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。",
@@ -51112,6 +51112,7 @@
"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 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 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 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 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 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 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。",
@@ -51137,11 +51138,10 @@
"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 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 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 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 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 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。"
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 17273, "summarizedRecords": 17274,
"version": 1 "version": 1
} }

1250
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1650
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.22.1", "agentVersion": "2026.09.22.1",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "181b7d0f86d96368d125e18987b42dd26cc434522766de870edf38bee253f460", ".modelhub_state/architecture_compatibility_blacklist.json": "29f7811f1b6a97f273d61c4374dc8c880bb692b652e38f9e96ac7c16017bec78",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "d527b8300f45ce773eb6995df34b8d9c916941e7939457821f07112fdfd33c5b", ".modelhub_state/market_intelligence.json": "2779f7a5ee2ab7cd4ca4340c5424c0d92b343dd1134f002407bd93e80b594139",
".modelhub_state/official_capabilities.json": "b2695c0aa997dd69be993b72010cca34176bd64501156126287ff79263d7876b", ".modelhub_state/official_capabilities.json": "84880869ff5ca3184c29607356431f48137e52e6266e9e698aa8c3ae13f48db1",
".modelhub_state/outcome_checkpoint.json": "5a022757eeb331aea8b0e6c4c06a9a05acdf6aaf629355560783aa97cd7f8848", ".modelhub_state/outcome_checkpoint.json": "d3ac8baad5c543fdba99f68ad077113064676fa74b22cfb9e2cc3867f8f127b7",
".modelhub_state/queue_cleanup_latest.json": "9e265d8a5474f7a5d1bd60df456c347c048806bef0f56f8bd7b220bb8e50c8b3", ".modelhub_state/queue_cleanup_latest.json": "9e265d8a5474f7a5d1bd60df456c347c048806bef0f56f8bd7b220bb8e50c8b3",
".modelhub_state/recent_outcomes.jsonl": "6ca02e17ab93c8578a1e3b64fa4ecefc028505ff16b84e9748ec2f30333d872b", ".modelhub_state/recent_outcomes.jsonl": "6ca02e17ab93c8578a1e3b64fa4ecefc028505ff16b84e9748ec2f30333d872b",
".modelhub_state/recovery_active_tasks.jsonl": "09e20acfd4bedc1b5a53bcab8b4c313e504453a88186dceb24043cd5bd5b8a78", ".modelhub_state/recovery_active_tasks.jsonl": "1a878df3591bb7e392854b672ee6154faaeb50095a360154f407edf6d3ac0e16",
".modelhub_state/recovery_intents.jsonl": "496f0316de7c51ea2f661d34790adaaea9699a72958dce93a312a3cae33ce54f", ".modelhub_state/recovery_intents.jsonl": "6905ae467496337824947e5e8be22872bb6929f441c6c6988685c9cbf8480988",
".modelhub_state/routing_intelligence.json": "519577e231ce3934d8378cbf1f13f1356f0576991f528675ded72ec2b8b3c804", ".modelhub_state/routing_intelligence.json": "519577e231ce3934d8378cbf1f13f1356f0576991f528675ded72ec2b8b3c804",
".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799", ".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
".modelhub_state/worker_crashes.jsonl": "ccd40ad86ab5068ea1c3520a48fa733cf2e4b357ae5abb95ff00728d5d1b5487", ".modelhub_state/worker_crashes.jsonl": "ccd40ad86ab5068ea1c3520a48fa733cf2e4b357ae5abb95ff00728d5d1b5487",
"ledger/submissions.jsonl": "23ba460d5e2ec5fac8ad0eca5544f4f4405d9cba4af0ac32f22689d65fc9fc4c", "ledger/submissions.jsonl": "23ba460d5e2ec5fac8ad0eca5544f4f4405d9cba4af0ac32f22689d65fc9fc4c",
"outcomes/submissions.jsonl": "f858862ea1bb33cc0a6ea5fbb6c28d882da12a3f48cc0e3d54a96a6e409b6921" "outcomes/submissions.jsonl": "c1abad5dfb6de23ca40cb2396dd1d58e3b985633b1fe8c0269c20c8fd92bd865"
}, },
"generation": 16858, "generation": 16859,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-26T22:38:18.833752+00:00", "updatedAt": "2026-09-26T22:40:12.090256+00:00",
"writerId": "08206cb1993a433e83f1d3e297db2d2e" "writerId": "08206cb1993a433e83f1d3e297db2d2e"
} }

1
outcomes/submissions.jsonl
View File

@@ -358,7 +358,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901659+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72670025872, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679340864, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int88", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679340864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.788367+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970568", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901659+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72670025872, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679340864, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int88", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679340864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.788367+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970568", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:21:49.901883+00:00", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673858, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "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": 7860673858}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.922099+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970574", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:21:49.901883+00:00", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673858, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "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": 7860673858}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.922099+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970574", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:21:49.902090+00:00", "modelId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245331488, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256941144, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2256941144}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.856488+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970570", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:21:49.902090+00:00", "modelId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245331488, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256941144, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2256941144}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.856488+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970570", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.902083+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142341, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 16568142341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:41.835421+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970584", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901918+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:42.093442+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970600", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901918+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:42.093442+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970600", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901870+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:15:36.946953+00:00", "targetGpu": "Vastai_va16", "taskId": "4970616", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901870+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:15:36.946953+00:00", "targetGpu": "Vastai_va16", "taskId": "4970616", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:34:29.856383+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:26:45.109939+00:00", "targetGpu": "Vastai_va16", "taskId": "4970729", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:34:29.856383+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:26:45.109939+00:00", "targetGpu": "Vastai_va16", "taskId": "4970729", "taskType": "text-generation", "verifyResult": null}