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

state: generation 35908 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-10-25 08:55:11 +00:00
parent dee714350c
commit bc5fb6f5de
7 changed files with 1746 additions and 1655 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -483,7 +483,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-25T08:53:26.137630+00:00", "generatedAt": "2026-10-25T08:55:03.826998+00:00",
"summary": { "summary": {
"activeBlockCount": 24, "activeBlockCount": 24,
"byGpuFramework": { "byGpuFramework": {

108
.modelhub_state/market_intelligence.json
View File

@@ -452,7 +452,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-25T08:53:26.261903+00:00", "generatedAt": "2026-10-25T08:55:03.962204+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
@@ -500,46 +500,46 @@
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 0.0017615764935232704, "backlogHours": 0.001761571321618884,
"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": 2.499999999817875, "qualityFactor": 2.5,
"queueFactor": 1.0, "queueFactor": 1.0,
"queueWeight": 1.0, "queueWeight": 1.0,
"recentSuccess": 340604, "recentSuccess": 340605,
"recentSuccessRate": 1.0, "recentSuccessRate": 1.0,
"recentTerminal": 340604, "recentTerminal": 340605,
"recentWilsonLowerBound": 0.9999887213401137, "recentWilsonLowerBound": 0.999988721373227,
"running": 0, "running": 0,
"selectionWeight": 2.499999999817875, "selectionWeight": 2.5,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 56767.333333333336, "throughputPerHour": 56767.5,
"waiting": 100 "waiting": 100
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 0.0017615764935232704, "backlogHours": 0.001761571321618884,
"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": 2.499999999817875, "qualityFactor": 2.5,
"queueFactor": 1.0, "queueFactor": 1.0,
"queueWeight": 1.0, "queueWeight": 1.0,
"recentSuccess": 340604, "recentSuccess": 340605,
"recentSuccessRate": 1.0, "recentSuccessRate": 1.0,
"recentTerminal": 340604, "recentTerminal": 340605,
"recentWilsonLowerBound": 0.9999887213401137, "recentWilsonLowerBound": 0.999988721373227,
"running": 0, "running": 0,
"selectionWeight": 2.499999999817875, "selectionWeight": 2.5,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 56767.333333333336, "throughputPerHour": 56767.5,
"waiting": 100 "waiting": 100
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
@@ -610,24 +610,24 @@
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 0.001761571321618884, "backlogHours": 0.0017615764935232704,
"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": 2.5, "qualityFactor": 2.499999999817875,
"queueFactor": 1.0, "queueFactor": 1.0,
"queueWeight": 1.0, "queueWeight": 1.0,
"recentSuccess": 340605, "recentSuccess": 340604,
"recentSuccessRate": 1.0, "recentSuccessRate": 1.0,
"recentTerminal": 340605, "recentTerminal": 340604,
"recentWilsonLowerBound": 0.999988721373227, "recentWilsonLowerBound": 0.9999887213401137,
"running": 0, "running": 0,
"selectionWeight": 2.5, "selectionWeight": 2.499999999817875,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 56767.5, "throughputPerHour": 56767.333333333336,
"waiting": 100 "waiting": 100
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
@@ -653,33 +653,11 @@
"waiting": 100 "waiting": 100
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true,
"backlogHours": 0.0017615764935232704,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.499999999817875,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 340604,
"recentSuccessRate": 1.0,
"recentTerminal": 340604,
"recentWilsonLowerBound": 0.9999887213401137,
"running": 0,
"selectionWeight": 2.499999999817875,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 56767.333333333336,
"waiting": 100
},
"Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 0.001761571321618884, "backlogHours": 0.001761571321618884,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Mthreads_s4000", "gpu": "MetaX_c-500",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 2.5, "qualityFactor": 2.5,
@@ -696,6 +674,28 @@
"throughputPerHour": 56767.5, "throughputPerHour": 56767.5,
"waiting": 100 "waiting": 100
}, },
"Mthreads_s4000": {
"available": true,
"backlogHours": 0.0017615764935232704,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.499999999817875,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 340604,
"recentSuccessRate": 1.0,
"recentTerminal": 340604,
"recentWilsonLowerBound": 0.9999887213401137,
"running": 0,
"selectionWeight": 2.499999999817875,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 56767.333333333336,
"waiting": 100
},
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 0.001761571321618884, "backlogHours": 0.001761571321618884,
@@ -742,30 +742,30 @@
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 0.001761571321618884, "backlogHours": 0.0017615764935232704,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "hygon_k100-ai", "gpu": "hygon_k100-ai",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 6, "maxConcurrentTasks": 6,
"qualityFactor": 2.5, "qualityFactor": 2.499999999817875,
"queueFactor": 1.0, "queueFactor": 1.0,
"queueWeight": 1.0, "queueWeight": 1.0,
"recentSuccess": 340605, "recentSuccess": 340604,
"recentSuccessRate": 1.0, "recentSuccessRate": 1.0,
"recentTerminal": 340605, "recentTerminal": 340604,
"recentWilsonLowerBound": 0.999988721373227, "recentWilsonLowerBound": 0.9999887213401137,
"running": 0, "running": 0,
"selectionWeight": 2.5, "selectionWeight": 2.499999999817875,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 56767.5, "throughputPerHour": 56767.333333333336,
"waiting": 100 "waiting": 100
} }
}, },
"queueAttemptedAt": "2026-10-25T08:44:40.956018+00:00", "queueAttemptedAt": "2026-10-25T08:55:03.962204+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-10-25T08:44:40.956018+00:00", "queueUpdatedAt": "2026-10-25T08:55:03.962204+00:00",
"supportedGpus": [ "supportedGpus": [
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",
"Vastai_va16", "Vastai_va16",

3178
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

80
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-25T08:50:12.350141+00:00", "generatedAt": "2026-10-25T08:55:03.733321+00:00",
"lastSyncTime": "2026-10-25T08:50:12.036043+00:00", "lastSyncTime": "2026-10-25T08:55:03.455509+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -913,11 +913,11 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 1, "decisionTotal": 1,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 158, "ambiguous_runtime": 159,
"memory_capacity": 1, "memory_capacity": 1,
"参数/模板问题": 11 "参数/模板问题": 11
}, },
"failureCount": 170, "failureCount": 171,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"pendingCount": 0, "pendingCount": 0,
@@ -927,8 +927,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 170, "total": 171,
"unresolvedFailureCount": 169 "unresolvedFailureCount": 170
}, },
"Biren_166m|vllm|text-generation": { "Biren_166m|vllm|text-generation": {
"attributableFailureCount": 51, "attributableFailureCount": 51,
@@ -3336,7 +3336,7 @@
"decisionSuccessRate": 0.0348, "decisionSuccessRate": 0.0348,
"decisionTotal": 201, "decisionTotal": 201,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 444, "ambiguous_runtime": 445,
"backend_operator": 11, "backend_operator": 11,
"framework_architecture_unsupported": 59, "framework_architecture_unsupported": 59,
"memory_capacity": 11, "memory_capacity": 11,
@@ -3345,15 +3345,15 @@
"tokenizer_compatibility": 100, "tokenizer_compatibility": 100,
"参数/模板问题": 45 "参数/模板问题": 45
}, },
"failureCount": 719, "failureCount": 720,
"failureRate": 0.9904, "failureRate": 0.9904,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 36, "platformFailureCount": 36,
"successCount": 7, "successCount": 7,
"successRate": 0.0096, "successRate": 0.0096,
"total": 726, "total": 727,
"unresolvedFailureCount": 489 "unresolvedFailureCount": 490
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"attributableFailureCount": 179, "attributableFailureCount": 179,
@@ -3384,7 +3384,7 @@
"unresolvedFailureCount": 358 "unresolvedFailureCount": 358
} }
}, },
"generatedAt": "2026-10-25T08:50:12.285947+00:00", "generatedAt": "2026-10-25T08:55:03.717990+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 133, "attributableFailureCount": 133,
@@ -3448,7 +3448,7 @@
"decisionSuccessRate": 0.1142, "decisionSuccessRate": 0.1142,
"decisionTotal": 219, "decisionTotal": 219,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 302, "ambiguous_runtime": 303,
"backend_operator": 4, "backend_operator": 4,
"context_length": 10, "context_length": 10,
"framework_architecture_unsupported": 126, "framework_architecture_unsupported": 126,
@@ -3462,15 +3462,15 @@
"日志缺失": 62, "日志缺失": 62,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 812, "failureCount": 813,
"failureRate": 0.9701, "failureRate": 0.9702,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 25, "successCount": 25,
"successRate": 0.0299, "successRate": 0.0298,
"total": 837, "total": 838,
"unresolvedFailureCount": 616 "unresolvedFailureCount": 617
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"attributableFailureCount": 771, "attributableFailureCount": 771,
@@ -7910,10 +7910,10 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 19, "ambiguous_runtime": 20,
"参数/模板问题": 3 "参数/模板问题": 3
}, },
"failureCount": 22, "failureCount": 23,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5", "modelType": "qwen3_5",
@@ -7925,8 +7925,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 22, "total": 23,
"unresolvedFailureCount": 22 "unresolvedFailureCount": 23
}, },
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_vl|none": { "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_vl|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -35311,6 +35311,30 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 30,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|32": { "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|32": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -62380,15 +62404,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 18071, "terminalRecords": 18072,
"totalRecords": 18615, "totalRecords": 18616,
"totals": { "totals": {
"attributableFailureCount": 6379, "attributableFailureCount": 6379,
"decisionFailureRate": 0.8661, "decisionFailureRate": 0.8661,
"decisionSuccessRate": 0.1339, "decisionSuccessRate": 0.1339,
"decisionTotal": 7365, "decisionTotal": 7365,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4692, "ambiguous_runtime": 4693,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 137, "backend_operator": 137,
@@ -62404,15 +62428,15 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 17085, "failureCount": 17086,
"failureRate": 0.9454, "failureRate": 0.9454,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 972, "platformFailureCount": 972,
"successCount": 986, "successCount": 986,
"successRate": 0.0546, "successRate": 0.0546,
"total": 18071, "total": 18072,
"unresolvedFailureCount": 9734 "unresolvedFailureCount": 9735
}, },
"warnings": [ "warnings": [
"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。",
@@ -62475,6 +62499,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 18615, "summarizedRecords": 18616,
"version": 1 "version": 1
} }

12
.modelhub_state/recovery_intents.jsonl
View File

@@ -3817,6 +3817,18 @@
{"batchId": "6d3bdabe2a5249f9bc3db33c70ac9281", "completedAt": "2026-10-25T06:27:11.237731+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-25T06:26:57.304528+00:00", "framework": "vllm-mlu", "intentId": "25e75a2e8d2449a1b86e96cf1248cdfb", "lastModified": "2026-10-21T14:42:38+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Jan-v1-4B-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-25T08:53:31.871188+00:00", "repoId": "cyankiwi/Jan-v1-4B-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5774395", "taskType": "text-generation"} {"batchId": "6d3bdabe2a5249f9bc3db33c70ac9281", "completedAt": "2026-10-25T06:27:11.237731+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-25T06:26:57.304528+00:00", "framework": "vllm-mlu", "intentId": "25e75a2e8d2449a1b86e96cf1248cdfb", "lastModified": "2026-10-21T14:42:38+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Jan-v1-4B-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-25T08:53:31.871188+00:00", "repoId": "cyankiwi/Jan-v1-4B-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5774395", "taskType": "text-generation"}
{"batchId": "ff056303094b4a07ba9c1b95c7767bc3", "completedAt": "2026-10-25T07:09:14.318969+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:09:11.995775+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dfacf96cec434d80b4771ba4de1b691f", "lastModified": "2026-10-24T12:01:13+00:00", "modelAddress": "https://modelscope.cn/models/kakarotter/calix", "reason": null, "reconciledAt": "2026-10-25T08:53:31.874455+00:00", "repoId": "kakarotter/calix", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5775023", "taskType": "text-generation"} {"batchId": "ff056303094b4a07ba9c1b95c7767bc3", "completedAt": "2026-10-25T07:09:14.318969+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:09:11.995775+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dfacf96cec434d80b4771ba4de1b691f", "lastModified": "2026-10-24T12:01:13+00:00", "modelAddress": "https://modelscope.cn/models/kakarotter/calix", "reason": null, "reconciledAt": "2026-10-25T08:53:31.874455+00:00", "repoId": "kakarotter/calix", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5775023", "taskType": "text-generation"}
{"batchId": "cb0e55bdd9604b6ea99538d87123023c", "completedAt": "2026-10-25T07:10:07.955116+00:00", "configFingerprint": "ab71f5b6f1f951bd7138e3540ab336b83cc96a774071c9d567b977c2e909eec3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:10:05.704943+00:00", "framework": "llamacpp", "intentId": "3cf6f6c0af08480aa0cbea9efb57f7c4", "lastModified": "2026-10-21T18:27:55+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/XHToken-Spark-X2.6-4B-GGUF", "reason": null, "reconciledAt": "2026-10-25T08:53:31.874452+00:00", "repoId": "prithivMLmods/XHToken-Spark-X2.6-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5775036", "taskType": "text-generation"} {"batchId": "cb0e55bdd9604b6ea99538d87123023c", "completedAt": "2026-10-25T07:10:07.955116+00:00", "configFingerprint": "ab71f5b6f1f951bd7138e3540ab336b83cc96a774071c9d567b977c2e909eec3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:10:05.704943+00:00", "framework": "llamacpp", "intentId": "3cf6f6c0af08480aa0cbea9efb57f7c4", "lastModified": "2026-10-21T18:27:55+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/XHToken-Spark-X2.6-4B-GGUF", "reason": null, "reconciledAt": "2026-10-25T08:53:31.874452+00:00", "repoId": "prithivMLmods/XHToken-Spark-X2.6-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5775036", "taskType": "text-generation"}
{"batchId": "419e472c7e8a4f2eb5326f4e5c139979", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:55:11.052639+00:00", "framework": "vllm_tokenizer_patch", "intentId": "24784b745191425abf31a1ae31cf3542", "lastModified": "2026-10-21T16:21:36+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Report-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "419e472c7e8a4f2eb5326f4e5c139979", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:55:11.052746+00:00", "framework": "vllm_tokenizer_patch", "intentId": "00eb50f38b874a6a99811db9fc25dd17", "lastModified": "2026-10-21T17:24:35+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Orchestrator-8B-AWQ-4bit", "repoId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "419e472c7e8a4f2eb5326f4e5c139979", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:55:11.052794+00:00", "framework": "vllm_tokenizer_patch", "intentId": "623ceca72fd9446c86a2b699cbdaa701", "lastModified": "2026-10-21T16:41:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "419e472c7e8a4f2eb5326f4e5c139979", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:55:11.052838+00:00", "framework": "vllm-mlu", "intentId": "2f52df44cb0047d085599c88881af644", "lastModified": "2026-10-21T16:38:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "419e472c7e8a4f2eb5326f4e5c139979", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:55:11.052893+00:00", "framework": "vllm-mlu", "intentId": "5125be6594434e41894bc4c21a28fa73", "lastModified": "2026-10-21T17:09:55+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "419e472c7e8a4f2eb5326f4e5c139979", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:55:11.052944+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a31c22e474624b119e947ccb54011c34", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "419e472c7e8a4f2eb5326f4e5c139979", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:55:11.052983+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1cac0f943d9c4159babd490c81f19c69", "lastModified": "2026-10-21T15:59:12+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "419e472c7e8a4f2eb5326f4e5c139979", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:55:11.053021+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bb6f978af8b841ce8b0e0ed65f68e6d4", "lastModified": "2026-10-21T16:02:35+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4.3-36B-AWQ-8bit", "repoId": "cyankiwi/Hermes-4.3-36B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "419e472c7e8a4f2eb5326f4e5c139979", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:55:11.053058+00:00", "framework": "vllm_tokenizer_patch", "intentId": "07a02e04af8f48a2b25b98da4354cf14", "lastModified": "2026-10-21T15:53:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "419e472c7e8a4f2eb5326f4e5c139979", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:55:11.053096+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c9c74c875a584385afb50034ce382343", "lastModified": "2026-10-21T15:51:34+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/granite-4.0-h-tiny-AWQ-8bit", "repoId": "cyankiwi/granite-4.0-h-tiny-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "419e472c7e8a4f2eb5326f4e5c139979", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:55:11.053133+00:00", "framework": "vllm_tokenizer_patch", "intentId": "11abbecca58244ffa6ef18f094fa6eb9", "lastModified": "2026-10-21T17:08:03+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-8bit", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "419e472c7e8a4f2eb5326f4e5c139979", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:55:11.053170+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2691de412dc44ef9b0b179e9cb1ec9d3", "lastModified": "2026-10-21T16:31:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "3c4cf7de36084654aa335d20b4101992", "completedAt": "2026-10-25T08:53:29.498463+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:53:27.083141+00:00", "framework": "vllm_tokenizer_patch", "intentId": "479d1b0e077d4f648de325bf15a95d52", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} {"batchId": "3c4cf7de36084654aa335d20b4101992", "completedAt": "2026-10-25T08:53:29.498463+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:53:27.083141+00:00", "framework": "vllm_tokenizer_patch", "intentId": "479d1b0e077d4f648de325bf15a95d52", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "3c4cf7de36084654aa335d20b4101992", "completedAt": "2026-10-25T08:53:29.498460+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:53:27.083104+00:00", "framework": "vllm_tokenizer_patch", "intentId": "745e88e6b3dc46be99ba76398e089215", "repoId": "cyankiwi/LFM2-8B-A1B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} {"batchId": "3c4cf7de36084654aa335d20b4101992", "completedAt": "2026-10-25T08:53:29.498460+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:53:27.083104+00:00", "framework": "vllm_tokenizer_patch", "intentId": "745e88e6b3dc46be99ba76398e089215", "repoId": "cyankiwi/LFM2-8B-A1B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "3c4cf7de36084654aa335d20b4101992", "completedAt": "2026-10-25T08:53:29.498457+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:53:27.083066+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c42d6c5cf17c412eaa2d60180a58aefb", "repoId": "cyankiwi/KAT-Dev-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} {"batchId": "3c4cf7de36084654aa335d20b4101992", "completedAt": "2026-10-25T08:53:29.498457+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T08:53:27.083066+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c42d6c5cf17c412eaa2d60180a58aefb", "repoId": "cyankiwi/KAT-Dev-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "4a53949e0e901623084b1677b2c25adec0bf8d18c7d7431724b9ec8e1f7628b0", ".modelhub_state/account_capacity.json": "4a53949e0e901623084b1677b2c25adec0bf8d18c7d7431724b9ec8e1f7628b0",
".modelhub_state/architecture_compatibility_blacklist.json": "373838dfad15f5ba8716a115455d55160f379dafde75144dc2a93b36a61a148a", ".modelhub_state/architecture_compatibility_blacklist.json": "a88d37401d182e7176ba1d7f4c1db1923ef4c510e4f764b65ead75ef9dcfe734",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "01292f74f9175a4ecf10a0df4e57f9dac25c2bf41fa7028b693886093019bb44", ".modelhub_state/market_intelligence.json": "0713bbadeb45a3835917a1937fd8eeb1025862ed1d73707d177392d7bdafbcba",
".modelhub_state/official_capabilities.json": "13d805a444ce9f2efe2a74e74b1092b06bd4cb4e1d1d93692181b8e962cf6fe9", ".modelhub_state/official_capabilities.json": "1ea110d2bf6d7f08866cf92f958fceb4c307b94e598de5899ce481915c07bffc",
".modelhub_state/outcome_checkpoint.json": "6dbec22af8cc1c58e15ed7ba89c0cad70aeeba19d9af74b505a6b1b2ac30f26d", ".modelhub_state/outcome_checkpoint.json": "24e57c87f7c3daf226d71b2bca9ae98185ca1051e3ba7b89381bedaccd20cfa3",
".modelhub_state/queue_cleanup_latest.json": "f15064e296338b59cf5c3f811b65220d085441e2df72782bf8768f8ba78e9ef4", ".modelhub_state/queue_cleanup_latest.json": "f15064e296338b59cf5c3f811b65220d085441e2df72782bf8768f8ba78e9ef4",
".modelhub_state/recent_outcomes.jsonl": "f2bf55e84fb382c2a4e1519919c32a8f629ce9fc550e070348dcf4f980b9e43d", ".modelhub_state/recent_outcomes.jsonl": "f2bf55e84fb382c2a4e1519919c32a8f629ce9fc550e070348dcf4f980b9e43d",
".modelhub_state/recovery_active_tasks.jsonl": "763f7731f4474c8fdbcf398d5898a2a0e94b6a5b8968def957d82ff627c16291", ".modelhub_state/recovery_active_tasks.jsonl": "763f7731f4474c8fdbcf398d5898a2a0e94b6a5b8968def957d82ff627c16291",
".modelhub_state/recovery_intents.jsonl": "70883f0abcf0238fcc512f4618edc382a1b7711e146c10ced24b24cd7bbafa2a", ".modelhub_state/recovery_intents.jsonl": "bfe7936ebfa0bb591aa3a214b77e6dd23da670ec1adbde87c387d75c596a49ef",
".modelhub_state/routing_intelligence.json": "3cf33d42a36b8df5ec1537f392694d0d2c17d39e8f62604aee5c3e640facb161", ".modelhub_state/routing_intelligence.json": "3cf33d42a36b8df5ec1537f392694d0d2c17d39e8f62604aee5c3e640facb161",
".modelhub_state/submission_exclusions.jsonl": "ec0164a066e590a129ed69be5c4279284ccf1a85230e402be88754b03203581d", ".modelhub_state/submission_exclusions.jsonl": "ec0164a066e590a129ed69be5c4279284ccf1a85230e402be88754b03203581d",
".modelhub_state/worker_crashes.jsonl": "3527d86c4fe5a43e8c0b1158e6f24e748474fce5a149c696caf4a1da895ac64a", ".modelhub_state/worker_crashes.jsonl": "3527d86c4fe5a43e8c0b1158e6f24e748474fce5a149c696caf4a1da895ac64a",
"ledger/submissions.jsonl": "23ffcc14e88cc38b1025d60b1fd771c64c7faa57f5c91f22c2ca4953d24316c1", "ledger/submissions.jsonl": "23ffcc14e88cc38b1025d60b1fd771c64c7faa57f5c91f22c2ca4953d24316c1",
"outcomes/submissions.jsonl": "4c0025f5e9a6dc0862f8d233257ababe12164e8d886019142625c128b896bf29" "outcomes/submissions.jsonl": "012a90692c5b166dba21b8d2062de89a71457ef44d1000707c242b868410ba6a"
}, },
"generation": 35907, "generation": 35908,
"phase": "cycle", "phase": "intent",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-25T08:53:32.073877+00:00", "updatedAt": "2026-10-25T08:55:11.280041+00:00",
"writerId": "750e06ff79b245419d079bcf827fbb45" "writerId": "750e06ff79b245419d079bcf827fbb45"
} }

3
outcomes/submissions.jsonl
View File

@@ -358,7 +358,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953115+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.663460+00:00", "targetGpu": "Biren_166m", "taskId": "5320469", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953115+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.663460+00:00", "targetGpu": "Biren_166m", "taskId": "5320469", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952000+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3677830216, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.674379+00:00", "targetGpu": "Biren_166m", "taskId": "5320468", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952000+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3677830216, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.674379+00:00", "targetGpu": "Biren_166m", "taskId": "5320468", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952449+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19336478290, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.749482+00:00", "targetGpu": "Biren_166m", "taskId": "5320478", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952449+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19336478290, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.749482+00:00", "targetGpu": "Biren_166m", "taskId": "5320478", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952558+00:00", "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1746942600, "estimatedRequiredGiB": 1.978, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 1769900320, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 1769900320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.760855+00:00", "targetGpu": "Biren_166m", "taskId": "5320477", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952675+00:00", "modelId": "NovelAI/novelai-lm-3b-508k", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12175174048, "estimatedRequiredGiB": 33.616, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 30079174063, "modelscopeLicense": "gpl-2.0", "modelscopeParams": null, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30079174063}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.860245+00:00", "targetGpu": "Biren_166m", "taskId": "5320479", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952675+00:00", "modelId": "NovelAI/novelai-lm-3b-508k", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12175174048, "estimatedRequiredGiB": 33.616, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 30079174063, "modelscopeLicense": "gpl-2.0", "modelscopeParams": null, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30079174063}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.860245+00:00", "targetGpu": "Biren_166m", "taskId": "5320479", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952883+00:00", "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.952740+00:00", "targetGpu": "Biren_166m", "taskId": "5320483", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952883+00:00", "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.952740+00:00", "targetGpu": "Biren_166m", "taskId": "5320483", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952339+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199612614, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199612614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.965681+00:00", "targetGpu": "Biren_166m", "taskId": "5320480", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952339+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199612614, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199612614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.965681+00:00", "targetGpu": "Biren_166m", "taskId": "5320480", "taskType": "text-generation", "verifyResult": null}
@@ -1086,7 +1085,7 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T07:37:52.053572+00:00", "modelId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115815143, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115815143}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T23:37:28.736824+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5768837", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T07:37:52.053572+00:00", "modelId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115815143, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115815143}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T23:37:28.736824+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5768837", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T07:41:11.585548+00:00", "modelId": "cyankiwi/GLM-4.5-Air-Derestricted-AWQ-4bit", "modelProfile": {"architectures": ["Glm4MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 63400571960, "estimatedRequiredGiB": 70.884, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "glm4_moe", "modelscopeFileSize": 63425673473, "modelscopeLicense": "mit", "modelscopeParams": 106852251264, "modelscopeTags": ["license:mit", "model_type:glm4_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:abliterated", "custom_tag:derestricted", "custom_tag:glm-4.5-air", "custom_tag:unlimited", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 63425673473}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T23:40:05.533470+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5768869", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T07:41:11.585548+00:00", "modelId": "cyankiwi/GLM-4.5-Air-Derestricted-AWQ-4bit", "modelProfile": {"architectures": ["Glm4MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 63400571960, "estimatedRequiredGiB": 70.884, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "glm4_moe", "modelscopeFileSize": 63425673473, "modelscopeLicense": "mit", "modelscopeParams": 106852251264, "modelscopeTags": ["license:mit", "model_type:glm4_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:abliterated", "custom_tag:derestricted", "custom_tag:glm-4.5-air", "custom_tag:unlimited", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 63425673473}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T23:40:05.533470+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5768869", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T08:51:49.349613+00:00", "modelId": "cyankiwi/KAT-Dev-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20666355744, "estimatedRequiredGiB": 23.114, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 20682426913, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32762123264, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20682426913}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T00:50:52.048251+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5769793", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T08:51:49.349613+00:00", "modelId": "cyankiwi/KAT-Dev-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20666355744, "estimatedRequiredGiB": 23.114, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 20682426913, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32762123264, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20682426913}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T00:50:52.048251+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5769793", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5368163296, "estimatedRequiredGiB": 6.019, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 5386102118, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5386102118}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T00:54:59.470899+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5769872", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T08:55:03.455483+00:00", "modelId": "cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5368163296, "estimatedRequiredGiB": 6.019, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 5386102118, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5386102118}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T00:54:59.470899+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5769872", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/KAT-Dev-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20666355744, "estimatedRequiredGiB": 23.114, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 20682426913, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32762123264, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-23T01:38:31.560801+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 20682426913}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T02:30:10.729769+00:00", "targetGpu": "MetaX_c-500", "taskId": "5771004", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/KAT-Dev-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20666355744, "estimatedRequiredGiB": 23.114, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 20682426913, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32762123264, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-23T01:38:31.560801+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 20682426913}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T02:30:10.729769+00:00", "targetGpu": "MetaX_c-500", "taskId": "5771004", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "kakarotter/calix", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2290347504, "estimatedRequiredGiB": 2.562, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 2292275515, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1145157120, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:pretraining"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2292275515}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T02:52:51.832672+00:00", "targetGpu": "MetaX_c-500", "taskId": "5771333", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "kakarotter/calix", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2290347504, "estimatedRequiredGiB": 2.562, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 2292275515, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1145157120, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:pretraining"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2292275515}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T02:52:51.832672+00:00", "targetGpu": "MetaX_c-500", "taskId": "5771333", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115902413, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115902413}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T03:12:43.268661+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5771609", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115902413, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115902413}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T03:12:43.268661+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5771609", "taskType": "text-generation", "verifyResult": null}