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

state: generation 13250 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-23 01:29:38 +00:00
parent 22794e7b02
commit 8437a5fcb5
8 changed files with 1740 additions and 1717 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -3023,7 +3023,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-23T01:25:27.978750+00:00", "generatedAt": "2026-09-23T01:29:16.689348+00:00",
"summary": { "summary": {
"activeBlockCount": 152, "activeBlockCount": 152,
"byGpuFramework": { "byGpuFramework": {

216
.modelhub_state/market_intelligence.json
View File

@@ -1,8 +1,8 @@
{ {
"communityAttemptedAt": "2026-09-23T01:13:28.990550+00:00", "communityAttemptedAt": "2026-09-23T01:29:32.152287+00:00",
"communityError": null, "communityError": null,
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": "2026-09-23T01:13:28.990550+00:00", "communityUpdatedAt": "2026-09-23T01:29:32.152287+00:00",
"frameworkAttemptedAt": "2026-09-22T22:43:53.208472+00:00", "frameworkAttemptedAt": "2026-09-22T22:43:53.208472+00:00",
"frameworkError": null, "frameworkError": null,
"frameworkStats": { "frameworkStats": {
@@ -396,99 +396,99 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-23T01:28:13.155029+00:00", "generatedAt": "2026-09-23T01:29:32.152287+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1275.9248120300751, "backlogHours": 1254.9777777777779,
"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": 2.2975414096653655, "qualityFactor": 1.9039851561039232,
"queueFactor": 0.9631952503965542, "queueFactor": 0.959640851243542,
"queueWeight": 0.9631952503965542, "queueWeight": 0.959640851243542,
"recentSuccess": 57, "recentSuccess": 58,
"recentSuccessRate": 0.42857142857142855, "recentSuccessRate": 0.42962962962962964,
"recentTerminal": 133, "recentTerminal": 135,
"recentWilsonLowerBound": 0.3476361863493269, "recentWilsonLowerBound": 0.34921160149343466,
"running": 8, "running": 9,
"selectionWeight": 2.212980973379084, "selectionWeight": 1.8271419359586372,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.166666666666668, "throughputPerHour": 22.5,
"waiting": 28283 "waiting": 28237
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 189.07407407407408, "backlogHours": 191.62025316455697,
"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": 0.27707984350433507, "qualityFactor": 0.20056777661681796,
"queueFactor": 1.2826060893963431, "queueFactor": 1.2721488252448303,
"queueWeight": 1.2826060893963431, "queueWeight": 1.2721488252448303,
"recentSuccess": 30, "recentSuccess": 28,
"recentSuccessRate": 0.18518518518518517, "recentSuccessRate": 0.17721518987341772,
"recentTerminal": 162, "recentTerminal": 158,
"recentWilsonLowerBound": 0.13290856549831656, "recentWilsonLowerBound": 0.12554945913041102,
"running": 8, "running": 8,
"selectionWeight": 0.35538429452764597, "selectionWeight": 0.25515206140505253,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 27.0, "throughputPerHour": 26.333333333333332,
"waiting": 5105 "waiting": 5046
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1899.75, "backlogHours": 1900.375,
"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": 0.9647802396746181, "qualityFactor": 0.7916049482162266,
"queueFactor": 0.9073683506463465, "queueFactor": 0.9017335666091757,
"queueWeight": 0.9073683506463465, "queueWeight": 0.9017335666091757,
"recentSuccess": 17, "recentSuccess": 17,
"recentSuccessRate": 0.3541666666666667, "recentSuccessRate": 0.3541666666666667,
"recentTerminal": 48, "recentTerminal": 48,
"recentWilsonLowerBound": 0.23433457112685732, "recentWilsonLowerBound": 0.23433457112685732,
"running": 7, "running": 7,
"selectionWeight": 0.8754110548097451, "selectionWeight": 0.7138167533004899,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.0, "throughputPerHour": 8.0,
"waiting": 15198 "waiting": 15203
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 443.219512195122, "backlogHours": 447.0,
"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": 0.31867223379343496, "qualityFactor": 0.26635569244272456,
"queueFactor": 1.1287435044375775, "queueFactor": 1.1203610558719406,
"queueWeight": 1.1287435044375775, "queueWeight": 1.1203610558719406,
"recentSuccess": 25, "recentSuccess": 25,
"recentSuccessRate": 0.2032520325203252, "recentSuccessRate": 0.20491803278688525,
"recentTerminal": 123, "recentTerminal": 122,
"recentWilsonLowerBound": 0.1416321145776123, "recentWilsonLowerBound": 0.14282861339624775,
"running": 7, "running": 7,
"selectionWeight": 0.3596992139389528, "selectionWeight": 0.29841454482263274,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 20.5, "throughputPerHour": 20.333333333333332,
"waiting": 9086 "waiting": 9089
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 44.24528301886792, "backlogHours": 44.38871473354232,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -497,20 +497,20 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 5, "recentSuccess": 3,
"recentSuccessRate": 0.015723270440251572, "recentSuccessRate": 0.009404388714733543,
"recentTerminal": 318, "recentTerminal": 319,
"recentWilsonLowerBound": 0.0067341567591421275, "recentWilsonLowerBound": 0.0032033371501954864,
"running": 24, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 53.0, "throughputPerHour": 53.166666666666664,
"waiting": 2345 "waiting": 2360
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 134.91666666666666, "backlogHours": 135.77777777777777,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-150", "gpu": "Iluvatar_bi-150",
@@ -528,7 +528,7 @@
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 36.0, "throughputPerHour": 36.0,
"waiting": 4857 "waiting": 4888
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
@@ -538,15 +538,15 @@
"gpu": "Iluvatar_mrv-100", "gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.6970171287812161, "qualityFactor": 0.5719045492896547,
"queueFactor": 0.8626840484268429, "queueFactor": 0.8573690571748939,
"queueWeight": 0.8626840484268429, "queueWeight": 0.8573690571748939,
"recentSuccess": 12, "recentSuccess": 12,
"recentSuccessRate": 0.3333333333333333, "recentSuccessRate": 0.3333333333333333,
"recentTerminal": 36, "recentTerminal": 36,
"recentWilsonLowerBound": 0.20214424774586046, "recentWilsonLowerBound": 0.20214424774586046,
"running": 2, "running": 2,
"selectionWeight": 0.6013055584798337, "selectionWeight": 0.4903332642185039,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.0, "throughputPerHour": 6.0,
@@ -554,140 +554,140 @@
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 452.4347826086956, "backlogHours": 442.0851063829787,
"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": 0.43416418711756444, "qualityFactor": 0.33926392256384197,
"queueFactor": 1.125264704895246, "queueFactor": 1.122220634911549,
"queueWeight": 1.125264704895246, "queueWeight": 1.122220634911549,
"recentSuccess": 31, "recentSuccess": 31,
"recentSuccessRate": 0.2246376811594203, "recentSuccessRate": 0.2198581560283688,
"recentTerminal": 138, "recentTerminal": 141,
"recentWilsonLowerBound": 0.1630090197301834, "recentWilsonLowerBound": 0.15943251615033457,
"running": 8, "running": 8,
"selectionWeight": 0.4885496358929305, "selectionWeight": 0.38072897458217736,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.0, "throughputPerHour": 23.5,
"waiting": 10406 "waiting": 10389
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 498.3230769230769, "backlogHours": 498.276923076923,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "MetaX_c-500", "gpu": "MetaX_c-500",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 0.3800082946761888, "qualityFactor": 0.31179789350819875,
"queueFactor": 1.109076351080476, "queueFactor": 1.1022586523330895,
"queueWeight": 1.109076351080476, "queueWeight": 1.1022586523330895,
"recentSuccess": 28, "recentSuccess": 28,
"recentSuccessRate": 0.2153846153846154, "recentSuccessRate": 0.2153846153846154,
"recentTerminal": 130, "recentTerminal": 130,
"recentWilsonLowerBound": 0.15343032935030532, "recentWilsonLowerBound": 0.15343032935030532,
"running": 4, "running": 5,
"selectionWeight": 0.42145821283978174, "selectionWeight": 0.3436819258986433,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 21.666666666666668, "throughputPerHour": 21.666666666666668,
"waiting": 10797 "waiting": 10796
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2275.9245283018868, "backlogHours": 2365.0588235294117,
"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": 0.8831092146491676, "queueFactor": 0.8726253809729951,
"queueWeight": 0.8831092146491676, "queueWeight": 0.8726253809729951,
"recentSuccess": 26, "recentSuccess": 27,
"recentSuccessRate": 0.49056603773584906, "recentSuccessRate": 0.5294117647058824,
"recentTerminal": 53, "recentTerminal": 51,
"recentWilsonLowerBound": 0.36124029356039444, "recentWilsonLowerBound": 0.39523071344726596,
"running": 4, "running": 4,
"selectionWeight": 2.207773036622919, "selectionWeight": 2.1815634524324876,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.833333333333334, "throughputPerHour": 8.5,
"waiting": 20104 "waiting": 20103
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 6325.2, "backlogHours": 7298.769230769231,
"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": 1.6755694160238255, "qualityFactor": 1.2789631739021758,
"queueFactor": 0.7575773042883662, "queueFactor": 0.7369137970432916,
"queueWeight": 0.7575773042883662, "queueWeight": 0.7369137970432916,
"recentSuccess": 8, "recentSuccess": 7,
"recentSuccessRate": 0.5333333333333333, "recentSuccessRate": 0.5384615384615384,
"recentTerminal": 15, "recentTerminal": 13,
"recentWilsonLowerBound": 0.3011663015105079, "recentWilsonLowerBound": 0.29143432431832045,
"running": 2, "running": 2,
"selectionWeight": 1.2693733613393616, "selectionWeight": 0.9424856087587921,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 2.5, "throughputPerHour": 2.1666666666666665,
"waiting": 15813 "waiting": 15814
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 3510.9599999999996, "backlogHours": 3511.4399999999996,
"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": 0.05, "qualityFactor": 0.05,
"queueFactor": 0.8275118327866977, "queueFactor": 0.8223966732616653,
"queueWeight": 0.8275118327866977, "queueWeight": 0.8223966732616653,
"recentSuccess": 0, "recentSuccess": 0,
"recentSuccessRate": 0.0, "recentSuccessRate": 0.0,
"recentTerminal": 25, "recentTerminal": 25,
"recentWilsonLowerBound": 0.0, "recentWilsonLowerBound": 0.0,
"running": 16, "running": 16,
"selectionWeight": 0.04137559163933489, "selectionWeight": 0.04111983366308327,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 4.166666666666667, "throughputPerHour": 4.166666666666667,
"waiting": 14629 "waiting": 14631
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 993.6969696969697, "backlogHours": 953.5882352941177,
"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": 0.5802505764413819, "qualityFactor": 0.4446668366328316,
"queueFactor": 1.0, "queueFactor": 1.0,
"queueWeight": 1.0, "queueWeight": 1.0,
"recentSuccess": 26, "recentSuccess": 26,
"recentSuccessRate": 0.26262626262626265, "recentSuccessRate": 0.2549019607843137,
"recentTerminal": 99, "recentTerminal": 102,
"recentWilsonLowerBound": 0.18598028163201125, "recentWilsonLowerBound": 0.1802954037747794,
"running": 6, "running": 6,
"selectionWeight": 0.5802505764413819, "selectionWeight": 0.4446668366328316,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 16.5, "throughputPerHour": 17.0,
"waiting": 16396 "waiting": 16211
} }
}, },
"queueAttemptedAt": "2026-09-23T01:18:28.478341+00:00", "queueAttemptedAt": "2026-09-23T01:29:32.152287+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-23T01:18:28.478341+00:00", "queueUpdatedAt": "2026-09-23T01:29:32.152287+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": "2026-09-23T01:28:13.155029+00:00", "catalogUpdatedAt": "2026-09-23T01:29:32.152287+00:00",
"configuredTaskTypes": [ "configuredTaskTypes": [
"text-generation" "text-generation"
], ],
@@ -56,7 +56,7 @@
"time-series-forecasting" "time-series-forecasting"
], ],
"errors": [], "errors": [],
"generatedAt": "2026-09-23T01:28:13.155029+00:00", "generatedAt": "2026-09-23T01:29:32.152287+00:00",
"gpuCatalog": { "gpuCatalog": {
"Ascend_910-b3": { "Ascend_910-b3": {
"canVerify": true, "canVerify": true,
@@ -6669,6 +6669,6 @@
"updateTime": "2025-12-22 08:59:53" "updateTime": "2025-12-22 08:59:53"
} }
], ],
"taskTreeUpdatedAt": "2026-09-23T01:28:13.155029+00:00", "taskTreeUpdatedAt": "2026-09-23T01:29:32.152287+00:00",
"version": 1 "version": 1
} }

94
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-23T01:25:27.901094+00:00", "generatedAt": "2026-09-23T01:29:16.600030+00:00",
"lastSyncTime": "2026-09-23T01:25:27.158548+00:00", "lastSyncTime": "2026-09-23T01:29:14.657262+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -4708,17 +4708,17 @@
"unresolvedFailureCount": 19 "unresolvedFailureCount": 19
}, },
"Kunlunxin_p-800|vllm|text-generation": { "Kunlunxin_p-800|vllm|text-generation": {
"attributableFailureCount": 9, "attributableFailureCount": 10,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 9, "decisionTotal": 10,
"failureBreakdown": { "failureBreakdown": {
"backend_operator": 2, "backend_operator": 2,
"framework_architecture_unsupported": 6, "framework_architecture_unsupported": 7,
"model_load": 1, "model_load": 1,
"参数/模板问题": 2 "参数/模板问题": 2
}, },
"failureCount": 11, "failureCount": 12,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -4728,7 +4728,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 11, "total": 12,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 2
}, },
"Kunlunxin_r-200-8f|unknown|text-generation": { "Kunlunxin_r-200-8f|unknown|text-generation": {
@@ -5691,17 +5691,17 @@
"unresolvedFailureCount": 6462 "unresolvedFailureCount": 6462
}, },
"vllm": { "vllm": {
"attributableFailureCount": 3571, "attributableFailureCount": 3572,
"decisionFailureRate": 0.9741, "decisionFailureRate": 0.9741,
"decisionSuccessRate": 0.0259, "decisionSuccessRate": 0.0259,
"decisionTotal": 3666, "decisionTotal": 3667,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1534, "ambiguous_runtime": 1534,
"architecture_compatibility": 112, "architecture_compatibility": 112,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 86, "backend_operator": 86,
"context_length": 161, "context_length": 161,
"framework_architecture_unsupported": 1327, "framework_architecture_unsupported": 1328,
"memory_capacity": 722, "memory_capacity": 722,
"model_load": 211, "model_load": 211,
"platform_infrastructure": 866, "platform_infrastructure": 866,
@@ -5710,14 +5710,14 @@
"tokenizer_compatibility": 413, "tokenizer_compatibility": 413,
"参数/模板问题": 48 "参数/模板问题": 48
}, },
"failureCount": 6019, "failureCount": 6020,
"failureRate": 0.9845, "failureRate": 0.9845,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 866, "platformFailureCount": 866,
"successCount": 95, "successCount": 95,
"successRate": 0.0155, "successRate": 0.0155,
"total": 6114, "total": 6115,
"unresolvedFailureCount": 1582 "unresolvedFailureCount": 1582
}, },
"vllm-customized": { "vllm-customized": {
@@ -5867,7 +5867,7 @@
"unresolvedFailureCount": 173 "unresolvedFailureCount": 173
} }
}, },
"generatedAt": "2026-09-23T01:25:27.887500+00:00", "generatedAt": "2026-09-23T01:29:16.587275+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 102, "attributableFailureCount": 102,
@@ -6093,14 +6093,14 @@
"unresolvedFailureCount": 717 "unresolvedFailureCount": 717
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"attributableFailureCount": 49, "attributableFailureCount": 50,
"decisionFailureRate": 0.9074, "decisionFailureRate": 0.9091,
"decisionSuccessRate": 0.0926, "decisionSuccessRate": 0.0909,
"decisionTotal": 54, "decisionTotal": 55,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 208, "ambiguous_runtime": 208,
"backend_operator": 10, "backend_operator": 10,
"framework_architecture_unsupported": 21, "framework_architecture_unsupported": 22,
"memory_capacity": 2, "memory_capacity": 2,
"model_load": 12, "model_load": 12,
"platform_infrastructure": 1, "platform_infrastructure": 1,
@@ -6110,14 +6110,14 @@
"日志缺失": 1, "日志缺失": 1,
"验证失败": 23 "验证失败": 23
}, },
"failureCount": 314, "failureCount": 315,
"failureRate": 0.9843, "failureRate": 0.9844,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 5, "successCount": 5,
"successRate": 0.0157, "successRate": 0.0156,
"total": 319, "total": 320,
"unresolvedFailureCount": 264 "unresolvedFailureCount": 264
}, },
"Kunlunxin_r-200-8f": { "Kunlunxin_r-200-8f": {
@@ -17519,14 +17519,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Kunlunxin_p-800|vllm|text-generation|qwen3_5|none": { "Kunlunxin_p-800|vllm|text-generation|qwen3_5|none": {
"attributableFailureCount": 1, "attributableFailureCount": 2,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 1, "decisionTotal": 2,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 1 "framework_architecture_unsupported": 2
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"modelType": "qwen3_5", "modelType": "qwen3_5",
@@ -17538,7 +17538,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Kunlunxin_p-800|vllm|text-generation|qwen3_vl|none": { "Kunlunxin_p-800|vllm|text-generation|qwen3_vl|none": {
@@ -41039,6 +41039,30 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Kunlunxin_p-800|vllm|text-generation|qwen3_5|none|35": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 35,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm|text-generation|qwen3_vl|none|34": { "Kunlunxin_p-800|vllm|text-generation|qwen3_vl|none|34": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -45541,20 +45565,20 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 16783, "terminalRecords": 16784,
"totalRecords": 16991, "totalRecords": 16992,
"totals": { "totals": {
"attributableFailureCount": 6007, "attributableFailureCount": 6008,
"decisionFailureRate": 0.8621, "decisionFailureRate": 0.8621,
"decisionSuccessRate": 0.1379, "decisionSuccessRate": 0.1379,
"decisionTotal": 6968, "decisionTotal": 6969,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4278, "ambiguous_runtime": 4278,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 113, "backend_operator": 113,
"context_length": 322, "context_length": 322,
"framework_architecture_unsupported": 2129, "framework_architecture_unsupported": 2130,
"memory_capacity": 1203, "memory_capacity": 1203,
"model_load": 525, "model_load": 525,
"platform_infrastructure": 929, "platform_infrastructure": 929,
@@ -45565,14 +45589,14 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 15822, "failureCount": 15823,
"failureRate": 0.9427, "failureRate": 0.9427,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 929, "platformFailureCount": 929,
"successCount": 961, "successCount": 961,
"successRate": 0.0573, "successRate": 0.0573,
"total": 16783, "total": 16784,
"unresolvedFailureCount": 8886 "unresolvedFailureCount": 8886
}, },
"warnings": [ "warnings": [
@@ -45630,6 +45654,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 16991, "summarizedRecords": 16992,
"version": 1 "version": 1
} }

1234
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1886
.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": "c1cc7262046bed420c4b2c22a1ab719fd3317369eb7e13926ffa339fa658d295", ".modelhub_state/architecture_compatibility_blacklist.json": "1a809badaeaa1bf58ac92b242910cdafc2febaa794b26419035d7758624cf513",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "42a3e974d01aae1d93983631e038cf8e408f9660c6072e6a0015fa00161cd1bb", ".modelhub_state/market_intelligence.json": "a4a395f60bf38abefe302f1224a0a0e8b98a73238b60ce3e4b9164a895200dfb",
".modelhub_state/official_capabilities.json": "ed5e40d770cd1e000f842aa0a04ff153ea54a6094abaf263ae4ca26630dd4cbc", ".modelhub_state/official_capabilities.json": "d0940b7d870e5e7a00b46d63a6fe3d45100fb07156a841c16cbf9d4132f80957",
".modelhub_state/outcome_checkpoint.json": "596b2b43e599848933e6f8b878a5775ed296fb6bf0b9a6d8dfecfb29d6d12132", ".modelhub_state/outcome_checkpoint.json": "ebc136e014c341cea692031b63dbd40c167cbcbc048164521213960fe3e8c0b7",
".modelhub_state/queue_cleanup_latest.json": "70b12a33050de2b7d18becf5530413055730ba9da8e6ce7b09a99877bc0fd590", ".modelhub_state/queue_cleanup_latest.json": "70b12a33050de2b7d18becf5530413055730ba9da8e6ce7b09a99877bc0fd590",
".modelhub_state/recent_outcomes.jsonl": "79b6d55284c3f75cc08ad11b8ab20e4edff0f39ec4effad3abbee12ed1b7e175", ".modelhub_state/recent_outcomes.jsonl": "79b6d55284c3f75cc08ad11b8ab20e4edff0f39ec4effad3abbee12ed1b7e175",
".modelhub_state/recovery_active_tasks.jsonl": "08e0cd4fc9609acd5126e28891007a6c14033e0b48400d5660bd1d2621dccc30", ".modelhub_state/recovery_active_tasks.jsonl": "b5d9541ecee3653a5ffa067ba4161cea423f781800cd308c6b054958d51ca296",
".modelhub_state/recovery_intents.jsonl": "2143c18e29737f649c44d5b752caa4a6717dae4622f1975d3d9f2cad71c1d300", ".modelhub_state/recovery_intents.jsonl": "61a63b313523ad6a17dbb1bff3706277ba50a58996013d02253b596dd49a04f6",
".modelhub_state/routing_intelligence.json": "39ec7b5e77e11b96887ed828d68b094ab47d4d4e68b51e1ea92f4df7a81ab3e3", ".modelhub_state/routing_intelligence.json": "39ec7b5e77e11b96887ed828d68b094ab47d4d4e68b51e1ea92f4df7a81ab3e3",
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
".modelhub_state/worker_crashes.jsonl": "81a279620f26a6ff30e7cd3dca4b86844ec41a0d30ffee7d8a4b03ab754d2d4c", ".modelhub_state/worker_crashes.jsonl": "81a279620f26a6ff30e7cd3dca4b86844ec41a0d30ffee7d8a4b03ab754d2d4c",
"ledger/submissions.jsonl": "e41ca1b41c2d9fe7c553e3c10665298fcb8b0ac7fb7114270dbe689bfb7c6207", "ledger/submissions.jsonl": "e41ca1b41c2d9fe7c553e3c10665298fcb8b0ac7fb7114270dbe689bfb7c6207",
"outcomes/submissions.jsonl": "cc01a682c7533897a3a986e4b2967121707a42f240cf3383fdaf7b56d9c5603b" "outcomes/submissions.jsonl": "0f422d3d971d689e3511f5a4d53fb5c4dec02881de45841d5c4c8356bb93af49"
}, },
"generation": 13249, "generation": 13250,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-23T01:28:13.827236+00:00", "updatedAt": "2026-09-23T01:29:38.675170+00:00",
"writerId": "0024d6b5efdf486184421da342f897ee" "writerId": "0024d6b5efdf486184421da342f897ee"
} }

1
outcomes/submissions.jsonl
View File

@@ -482,7 +482,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T21:06:45.850274+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "2026-09-20T13:01:42.205703+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979280", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T21:06:45.850274+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "2026-09-20T13:01:42.205703+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979280", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T21:33:11.158023+00:00", "modelId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161034, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:19:23.910185+00:00", "targetGpu": "Vastai_va16", "taskId": "4979588", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T21:33:11.158023+00:00", "modelId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161034, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:19:23.910185+00:00", "targetGpu": "Vastai_va16", "taskId": "4979588", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T22:24:01.251269+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1232060880, "estimatedRequiredGiB": 1.379, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233909203, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233909203}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:22:13.035851+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4980360", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T22:24:01.251269+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1232060880, "estimatedRequiredGiB": 1.379, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233909203, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233909203}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:22:13.035851+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4980360", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T22:27:36.960787+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 36679335352, "estimatedRequiredGiB": 41.028, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 36711610638, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18339618304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:pruning", "custom_tag:width-pruning", "custom_tag:zero-training", "custom_tag:qwen3_5", "custom_tag:gated-deltanet"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36711610638}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:25:29.955385+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4980395", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754872+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "pending", "status": "waiting", "submitTime": "2026-09-20T14:37:47.734979+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980559", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754872+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "pending", "status": "waiting", "submitTime": "2026-09-20T14:37:47.734979+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980559", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754864+00:00", "modelId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7003604832, "estimatedRequiredGiB": 7.829, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7005626505, "modelscopeLicense": "llama2", "modelscopeParams": 6738415616, "modelscopeTags": ["license:llama2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7005626505}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:37:47.739015+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980560", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754864+00:00", "modelId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7003604832, "estimatedRequiredGiB": 7.829, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7005626505, "modelscopeLicense": "llama2", "modelscopeParams": 6738415616, "modelscopeTags": ["license:llama2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7005626505}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:37:47.739015+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980560", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754909+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096457730, "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": 4096457730}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:38:07.337494+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4980575", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754909+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096457730, "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": 4096457730}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:38:07.337494+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4980575", "taskType": "text-generation", "verifyResult": null}