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

state: generation 11141 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 03:31:26 +00:00
parent 12338311ce
commit d3b873e655
9 changed files with 2033 additions and 2046 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2062,6 +2062,25 @@
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation"
},
"vastai_va16|vllm_fix_tokenizer|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-20T03:41:42.245581+00:00",
"framework": "vllm_fix_tokenizer",
"latestFailureAt": "2026-09-20T03:41:42.245581+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed"
],
"sourceTaskIds": [
"4969995"
],
"targetGpu": "Vastai_va16",
"taskType": "text-generation"
},
"vastai_va16|vllm_fix_tokenizer|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
@@ -2431,9 +2450,9 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T03:25:55.946579+00:00",
"generatedAt": "2026-09-21T03:29:41.794294+00:00",
"summary": {
"activeBlockCount": 120,
"activeBlockCount": 121,
"byGpuFramework": {
"Ascend_910-b3|vllm": 13,
"Ascend_910-b3|vllm_tokenizer_patch": 5,
@@ -2454,7 +2473,7 @@
"Sunrise_pt-200-x1|vllm": 3,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 3,
"Vastai_va16|vllm": 16,
"Vastai_va16|vllm_fix_tokenizer": 2,
"Vastai_va16|vllm_fix_tokenizer": 3,
"hygon_k100-ai|vllm": 8,
"hygon_k100-ai|vllm-patch-tokenizer": 3
},

2
.modelhub_state/market_intelligence.json
View File

@@ -425,7 +425,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-21T03:28:37.563078+00:00",
"generatedAt": "2026-09-21T03:29:54.918940+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

3502
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

187
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T03:25:55.875915+00:00",
"lastSyncTime": "2026-09-21T03:25:53.878060+00:00",
"generatedAt": "2026-09-21T03:29:54.852621+00:00",
"lastSyncTime": "2026-09-21T03:29:54.793294+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2066,6 +2066,25 @@
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation"
},
"vastai_va16|vllm_fix_tokenizer|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-20T03:41:42.245581+00:00",
"framework": "vllm_fix_tokenizer",
"latestFailureAt": "2026-09-20T03:41:42.245581+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed"
],
"sourceTaskIds": [
"4969995"
],
"targetGpu": "Vastai_va16",
"taskType": "text-generation"
},
"vastai_va16|vllm_fix_tokenizer|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
@@ -2436,7 +2455,7 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 120,
"activeBlockCount": 121,
"byGpuFramework": {
"Ascend_910-b3|vllm": 13,
"Ascend_910-b3|vllm_tokenizer_patch": 5,
@@ -2457,7 +2476,7 @@
"Sunrise_pt-200-x1|vllm": 3,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 3,
"Vastai_va16|vllm": 16,
"Vastai_va16|vllm_fix_tokenizer": 2,
"Vastai_va16|vllm_fix_tokenizer": 3,
"hygon_k100-ai|vllm": 8,
"hygon_k100-ai|vllm-patch-tokenizer": 3
},
@@ -4684,26 +4703,26 @@
"unresolvedFailureCount": 3
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 11,
"decisionFailureRate": 0.6875,
"decisionSuccessRate": 0.3125,
"decisionTotal": 16,
"attributableFailureCount": 12,
"decisionFailureRate": 0.7059,
"decisionSuccessRate": 0.2941,
"decisionTotal": 17,
"failureBreakdown": {
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 9,
"framework_architecture_unsupported": 10,
"model_load": 2
},
"failureCount": 22,
"failureRate": 0.8148,
"failureCount": 23,
"failureRate": 0.8214,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 5,
"successRate": 0.1852,
"successRate": 0.1786,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 27,
"total": 28,
"unresolvedFailureCount": 11
},
"Vastai_va16|vllm|text-generation": {
@@ -5163,28 +5182,28 @@
"unresolvedFailureCount": 23
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 120,
"decisionFailureRate": 0.96,
"decisionSuccessRate": 0.04,
"decisionTotal": 125,
"attributableFailureCount": 121,
"decisionFailureRate": 0.9603,
"decisionSuccessRate": 0.0397,
"decisionTotal": 126,
"failureBreakdown": {
"ambiguous_runtime": 132,
"backend_operator": 8,
"framework_architecture_unsupported": 21,
"framework_architecture_unsupported": 22,
"memory_capacity": 7,
"model_load": 2,
"platform_infrastructure": 16,
"tokenizer_compatibility": 82,
"参数/模板问题": 9
},
"failureCount": 277,
"failureCount": 278,
"failureRate": 0.9823,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 5,
"successRate": 0.0177,
"total": 282,
"total": 283,
"unresolvedFailureCount": 141
},
"vllm_tokenizer_patch": {
@@ -5211,7 +5230,7 @@
"unresolvedFailureCount": 59
}
},
"generatedAt": "2026-09-21T03:25:55.865318+00:00",
"generatedAt": "2026-09-21T03:29:54.842928+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 90,
@@ -5565,14 +5584,14 @@
"unresolvedFailureCount": 422
},
"Vastai_va16": {
"attributableFailureCount": 443,
"decisionFailureRate": 0.886,
"decisionSuccessRate": 0.114,
"decisionTotal": 500,
"attributableFailureCount": 444,
"decisionFailureRate": 0.8862,
"decisionSuccessRate": 0.1138,
"decisionTotal": 501,
"failureBreakdown": {
"ambiguous_runtime": 811,
"context_length": 9,
"framework_architecture_unsupported": 188,
"framework_architecture_unsupported": 189,
"memory_capacity": 133,
"model_load": 44,
"platform_infrastructure": 14,
@@ -5582,14 +5601,14 @@
"日志缺失": 124,
"验证失败": 130
},
"failureCount": 1760,
"failureCount": 1761,
"failureRate": 0.9686,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 14,
"successCount": 57,
"successRate": 0.0314,
"total": 1817,
"total": 1818,
"unresolvedFailureCount": 1303
},
"hygon_k100-ai": {
@@ -5641,7 +5660,7 @@
"hygon_k100-ai": 64.0
},
"pendingRecords": 0,
"policyCancelledRecords": 173,
"policyCancelledRecords": 177,
"profileCombinationStats": {
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|bailing_hybrid|none": {
"attributableFailureCount": 1,
@@ -13248,14 +13267,14 @@
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
@@ -13267,7 +13286,7 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3|none": {
@@ -13944,31 +13963,6 @@
"total": 14,
"unresolvedFailureCount": 6
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-17T10:44:59.509445+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -14538,26 +14532,28 @@
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"decisionFailureRate": 0.5,
"decisionSuccessRate": 0.5,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 0.5,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T01:35:45.556154+00:00",
"lastTerminalAt": "2026-09-21T03:29:39.969809+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 1.0,
"successRate": 0.5,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm|text-generation": {
@@ -18197,6 +18193,31 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-21T03:29:39.969809+00:00",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
@@ -29513,14 +29534,14 @@
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
@@ -29533,7 +29554,7 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3|none|13": {
@@ -30188,20 +30209,20 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 16066,
"totalRecords": 16239,
"terminalRecords": 16067,
"totalRecords": 16244,
"totals": {
"attributableFailureCount": 5833,
"attributableFailureCount": 5834,
"decisionFailureRate": 0.8616,
"decisionSuccessRate": 0.1384,
"decisionTotal": 6770,
"decisionTotal": 6771,
"failureBreakdown": {
"ambiguous_runtime": 3841,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
"context_length": 318,
"framework_architecture_unsupported": 2037,
"framework_architecture_unsupported": 2038,
"memory_capacity": 1197,
"model_load": 489,
"platform_infrastructure": 922,
@@ -30212,14 +30233,14 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15129,
"failureCount": 15130,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 937,
"successRate": 0.0583,
"total": 16066,
"total": 16067,
"unresolvedFailureCount": 8374
},
"warnings": [
@@ -30273,6 +30294,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16239,
"summarizedRecords": 16244,
"version": 1
}

295
.modelhub_state/queue_cleanup_latest.json
View File

@@ -14,17 +14,18 @@
100
],
"accounts": 12,
"activeScanned": 1170,
"activeScanned": 1165,
"ageCleanupMode": "admission_only",
"agePolicySkipped": {
"cleanupDisabled": true,
"reason": "admission_only"
},
"architectureBlockCount": 120,
"architectureBlockCount": 121,
"architectureFrameworkCatalog": {
"ascend_910-b3|text-generation": [
"llamacpp",
"vllm",
"vllm_0.23.0",
"vllm_tokenizer_patch"
],
"ascend_910-b4|text-generation": [
@@ -72,132 +73,90 @@
]
},
"architectureFrameworkCatalogErrors": {},
"architectureIncompatibleCount": 6,
"architectureIncompatibleCount": 4,
"architectureIncompatibleTasks": [
{
"accountIndex": 2,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureBlockExpiresAt": "2026-10-20T03:41:42.245581+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignature": "model_type:qwen3_5",
"architectureSignatures": [
"model_type:qwen3_5_moe"
"model_type:qwen3_5"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
"vllm_fix_tokenizer"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
"framework": "vllm_fix_tokenizer",
"gpuType": "Vastai_va16",
"modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4938406,
"taskId": 4919175,
"taskType": "text-generation"
},
{
"accountIndex": 7,
"accountIndex": 5,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureBlockExpiresAt": "2026-10-20T03:41:42.245581+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignature": "model_type:qwen3_5",
"architectureSignatures": [
"model_type:qwen3_5_moe"
"model_type:qwen3_5"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
"vllm_fix_tokenizer"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "Edge0/Edge0-35B-A3B-preview",
"framework": "vllm_fix_tokenizer",
"gpuType": "Vastai_va16",
"modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4844610,
"taskId": 4735789,
"taskType": "text-generation"
},
{
"accountIndex": 6,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T03:41:42.245581+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5",
"architectureSignatures": [
"model_type:qwen3_5"
],
"evaluatedFrameworks": [
"vllm_fix_tokenizer"
],
"framework": "vllm_fix_tokenizer",
"gpuType": "Vastai_va16",
"modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4782467,
"taskType": "text-generation"
},
{
"accountIndex": 8,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureBlockExpiresAt": "2026-10-20T03:41:42.245581+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignature": "model_type:qwen3_5",
"architectureSignatures": [
"model_type:qwen3_5_moe"
"model_type:qwen3_5"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
"vllm_fix_tokenizer"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B",
"framework": "vllm_fix_tokenizer",
"gpuType": "Vastai_va16",
"modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4857321,
"taskType": "text-generation"
},
{
"accountIndex": 8,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4923309,
"taskType": "text-generation"
},
{
"accountIndex": 9,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4845112,
"taskType": "text-generation"
},
{
"accountIndex": 9,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4857320,
"taskId": 4919177,
"taskType": "text-generation"
}
],
@@ -229,162 +188,114 @@
"frameworkCatalogUnknown": 0,
"frameworkContextUnknown": 70,
"modelArchitectureUnknown": 134,
"noMatchingBlock": 1007,
"noMatchingBlock": 1004,
"partiallyBlockedFrameworkSet": 23,
"runningMatchedProtected": 0,
"submissionContextMismatch": 0,
"submissionContextUnknown": 0
},
"cancelledCount": 6,
"cancelledCount": 4,
"cancelledTasks": [
{
"accountIndex": 2,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureBlockExpiresAt": "2026-10-20T03:41:42.245581+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignature": "model_type:qwen3_5",
"architectureSignatures": [
"model_type:qwen3_5_moe"
"model_type:qwen3_5"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
"vllm_fix_tokenizer"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
"framework": "vllm_fix_tokenizer",
"gpuType": "Vastai_va16",
"modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4938406,
"taskId": 4919175,
"taskType": "text-generation"
},
{
"accountIndex": 7,
"accountIndex": 5,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureBlockExpiresAt": "2026-10-20T03:41:42.245581+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignature": "model_type:qwen3_5",
"architectureSignatures": [
"model_type:qwen3_5_moe"
"model_type:qwen3_5"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
"vllm_fix_tokenizer"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "Edge0/Edge0-35B-A3B-preview",
"framework": "vllm_fix_tokenizer",
"gpuType": "Vastai_va16",
"modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4844610,
"taskId": 4735789,
"taskType": "text-generation"
},
{
"accountIndex": 6,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T03:41:42.245581+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5",
"architectureSignatures": [
"model_type:qwen3_5"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm_fix_tokenizer"
],
"framework": "vllm_fix_tokenizer",
"gpuType": "Vastai_va16",
"modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4782467,
"taskType": "text-generation"
},
{
"accountIndex": 8,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureBlockExpiresAt": "2026-10-20T03:41:42.245581+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignature": "model_type:qwen3_5",
"architectureSignatures": [
"model_type:qwen3_5_moe"
"model_type:qwen3_5"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
"vllm_fix_tokenizer"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B",
"framework": "vllm_fix_tokenizer",
"gpuType": "Vastai_va16",
"modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4857321,
"taskType": "text-generation"
},
{
"accountIndex": 8,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4923309,
"taskType": "text-generation"
},
{
"accountIndex": 9,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4845112,
"taskType": "text-generation"
},
{
"accountIndex": 9,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4857320,
"taskId": 4919177,
"taskType": "text-generation"
}
],
"certainOomCount": 0,
"certainOomTasks": [],
"cleanupCandidateCount": 6,
"cleanupCandidateCount": 4,
"dryRun": false,
"listingErrors": {},
"modelAgeErrors": {},
@@ -409,7 +320,7 @@
],
"oldOverflowCount": 0,
"oldOverflowTasks": [],
"policyCancelledRecorded": 6,
"policyCancelledRecorded": 4,
"policyNoLongerAppliesCount": 0,
"policyNoLongerAppliesTasks": [],
"recentModelDays": 7,

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -155,6 +155,7 @@
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:01:00.671259+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19342796520, "estimatedRequiredGiB": 21.64, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 19362750397, "modelscopeLicense": "other", "modelscopeParams": 18237772608, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19362750397}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:48.972177+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969999", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T16:51:24.761963+00:00", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 10270608122}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:48.969580+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4969996", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T02:15:17.867223+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T03:41:48.960695+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970000", "taskType": "text-generation", "verifyResult": null}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T03:29:39.969809+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:42.245581+00:00", "targetGpu": "Vastai_va16", "taskId": "4969995", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T00:42:10.765065+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109841981, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109841981}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:30:31.100436+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969813", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T00:42:10.765058+00:00", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 10270608122}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:25:33.082653+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969693", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:37:54.215258+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:25:32.546681+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969665", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-17T14:07:00.815606+00:00", "modelId": "BAAI/CareBot_Medical_multi-llama3-8b-instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-17T14:01:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471928", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-17T13:39:06.611611+00:00", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T13:33:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4490702", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-17T11:44:39.929678+00:00", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T11:41:22+00:00", "targetGpu": "Biren_166m", "taskId": "4610390", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-17T10:44:59.509445+00:00", "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T10:41:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497070", "taskType": "text-generation", "verifyResult": -1}

39
.modelhub_state/recovery_intents.jsonl
View File

@@ -1964,6 +1964,45 @@
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788713+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.555968+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b21c2e9db2fc42c3899ad1b494c0bf78", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "reason": null, "reconciledAt": "2026-09-21T03:26:07.992037+00:00", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4992751", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788728+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.556971+00:00", "framework": "vllm_fix_tokenizer", "intentId": "173ec5f2cbbc4148b47133e20aeaa56d", "lastModified": "2026-08-24T19:35:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "reason": null, "reconciledAt": "2026-09-21T03:26:07.990462+00:00", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4992749", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788748+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557149+00:00", "framework": "vllm", "intentId": "c2fd8f6e6f8447f08128dc9542eeef2d", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "reason": null, "reconciledAt": "2026-09-21T03:26:07.992040+00:00", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4992750", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.915809+00:00", "framework": "vllm-mlu", "intentId": "76be1ce98a3341a7964d195b4b642cf1", "lastModified": "2026-08-24T19:57:49+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.915946+00:00", "framework": "vllm", "intentId": "ac6e717b91174964a23ade280448eec1", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916012+00:00", "framework": "vllm", "intentId": "d7fc7f1ba6ed45dd9a51efb9f981ee2a", "lastModified": "2026-08-24T19:39:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916071+00:00", "framework": "vllm", "intentId": "61d63a6ccd3340d6b4fea670ea1b5ca5", "lastModified": "2026-08-24T19:26:17+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916129+00:00", "framework": "vllm", "intentId": "45b4a9deae0d4bbabb4f8766413aa7d2", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916185+00:00", "framework": "vllm", "intentId": "ab948f0893994eb8aa94273c5558ab57", "lastModified": "2026-08-24T19:41:12+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916261+00:00", "framework": "vllm", "intentId": "64da38ea966c46b8a74cdc0b2eaaea71", "lastModified": "2026-08-24T19:25:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-2-7b-chat-quantized.w8a8", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916318+00:00", "framework": "vllm", "intentId": "ed3be3b217824885962babaf013e2ed7", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916376+00:00", "framework": "vllm", "intentId": "68bc162aa0844e4284a845aa0ba14e0d", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916432+00:00", "framework": "vllm", "intentId": "6ef3a7ba94bf49b6b39da26256e92c12", "lastModified": "2026-08-24T19:39:28+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916489+00:00", "framework": "vllm", "intentId": "2a310fdfeb6948b88e676975b459ea3c", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916545+00:00", "framework": "vllm", "intentId": "367ab53c73dc4ccbaf239d260ca90ee7", "lastModified": "2026-08-24T19:51:52+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916602+00:00", "framework": "vllm", "intentId": "b184014393244514b5377d5fec6186f3", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916685+00:00", "framework": "vllm", "intentId": "4705cd18d56c42faa6ac5d499f312345", "lastModified": "2026-08-24T19:36:07+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916742+00:00", "framework": "vllm", "intentId": "bb73a70033174ea485d284d2fb8a4dfd", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916799+00:00", "framework": "vllm", "intentId": "333da8e78700497f86efe425814f8d7a", "lastModified": "2026-09-01T03:52:21+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916855+00:00", "framework": "vllm", "intentId": "984c19e520f948e18fd755632b6111e4", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916911+00:00", "framework": "vllm", "intentId": "4f6a2634b6de487ba8a7febca7c85a7c", "lastModified": "2026-08-26T16:41:36+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.916967+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3a095c29ea06442d87ea76afb5b19112", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917011+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b24cb140ba1f47dba672268d18f71682", "lastModified": "2026-08-24T19:34:42+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917054+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e7ec3deb0ed84ba6bfc0e79df5ddad29", "lastModified": "2026-08-24T19:35:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917117+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f67e0c240c094e77a2c085d2cea11de5", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917161+00:00", "framework": "vllm-patch-tokenizer", "intentId": "2a79316537bc4c8889d64413778d0f49", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917203+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a8b9a42a43ad4b37b44be84f9817d74a", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917244+00:00", "framework": "vllm-patch-tokenizer", "intentId": "8c9e4a5eb9d2448d83abdf6de0b9c9b6", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917286+00:00", "framework": "vllm-patch-tokenizer", "intentId": "1064a52752a14895941c3e189e48c3bb", "lastModified": "2026-08-24T19:48:09+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917328+00:00", "framework": "vllm-patch-tokenizer", "intentId": "d55636b631f64a42914c6bc49a8b4402", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917370+00:00", "framework": "vllm-patch-tokenizer", "intentId": "113d490466a444aea5ab74feb5f4cdd2", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917412+00:00", "framework": "vllm-patch-tokenizer", "intentId": "63fd289b3ae649fc9ef03b538ce4290b", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917453+00:00", "framework": "vllm-patch-tokenizer", "intentId": "82fe06c330754cdc91ae5e42ebf6aa0b", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917495+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c998e4c34ee54ae98a72906483573160", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917537+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a17564d5fcf9434e813fbcd644b54843", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917580+00:00", "framework": "vllm", "intentId": "9db5eab9b167467eb4c6977d5694b4dc", "lastModified": "2026-08-24T19:34:25+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917629+00:00", "framework": "vllm", "intentId": "f2184c3386fd43b18511439df7bd57bd", "lastModified": "2026-08-24T20:10:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917711+00:00", "framework": "vllm", "intentId": "96a4efa47d7e4bdaa013ce8991bd22ed", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917758+00:00", "framework": "vllm", "intentId": "213b1ff85f3a4f2c889a6a211d572e9e", "lastModified": "2026-08-26T17:29:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917805+00:00", "framework": "vllm-customized", "intentId": "c4e5d6f31aa24e8d8b9fcce353fbef3b", "lastModified": "2026-09-09T12:19:20+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917864+00:00", "framework": "vllm-customized", "intentId": "5e22e8e24b454a55a98e373782db36c0", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "628cbab19008401890f93ee23b04e4cc", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:31:25.917939+00:00", "framework": "vllm-customized", "intentId": "b238b2d1c10245989269d0b8ecb72cec", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "f9cdc27b47ba4b13983993761fdd66b5", "completedAt": "2026-09-21T03:23:14.325695+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:19:27.210517+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7732ad2ea5be46feada0b01bf52f53c1", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "f9cdc27b47ba4b13983993761fdd66b5", "completedAt": "2026-09-21T03:23:14.325692+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:19:27.210462+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e4bd3633900547b6a3f6d0560772820a", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "f9cdc27b47ba4b13983993761fdd66b5", "completedAt": "2026-09-21T03:23:14.325689+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:19:27.210409+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ea0b893b15e24885a9f3338f626d8982", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}

22
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.20.2",
"checksums": {
".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f",
".modelhub_state/architecture_compatibility_blacklist.json": "3fa8e5b2eb0b45a2e4a685b8a9be71ee07940af854e95fc009918bf0a3a138ce",
".modelhub_state/architecture_compatibility_blacklist.json": "19fe9b1d25ebcfdefdb99f08bf2e52228ad453cf54309ecc21d028a43f07c69d",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "8ed940a2792eca83ffb314400f65ad3bd4b148c0a112610df371ceda210fc6f6",
".modelhub_state/official_capabilities.json": "1a2b1b709f026f6a8eabb542cca52ecdced4ea93ce4d532ab81239ffca3972b7",
".modelhub_state/outcome_checkpoint.json": "2fdf6795fd20b828473fcd2f721acec09e1e839d235752c68c32a5b3481fd76d",
".modelhub_state/queue_cleanup_latest.json": "294596e0492bf1839a4c2e817f44101a0d6d6c4779bf685b402ef658b7bffabd",
".modelhub_state/recent_outcomes.jsonl": "36ddbaf0408b38e38c39a90389c1b2fef4c8bfffb9c61858b67a2989855f9b29",
".modelhub_state/market_intelligence.json": "5be874fa0e533f5a2ccc354ea5c1b6e6da0697f5f8451660ded520dd71be23cf",
".modelhub_state/official_capabilities.json": "697da76aae430edcf77f2305f3cdb587f09167edbc5b988b699e8202fdb3b1fc",
".modelhub_state/outcome_checkpoint.json": "01881f9aaf06e32fa6b247edb86fc02aae183a278326e5583398f8ae7f1373a7",
".modelhub_state/queue_cleanup_latest.json": "86e75bc67974dfd9276f9856d5cfeb59b3038a10d88581f9a8560a20a9c91eee",
".modelhub_state/recent_outcomes.jsonl": "914bec3c62e52b1be43577fce011f1924adaf970f434a80e20a46e3e1f5709fd",
".modelhub_state/recovery_active_tasks.jsonl": "86656246a64b0aaff49c54028af8d39b243f28169e87c2f38d7c081daf15f460",
".modelhub_state/recovery_intents.jsonl": "af6d436735ea78c3e730483f77178f1590f066c4b9e9fd9894cd9bc2279169b0",
".modelhub_state/recovery_intents.jsonl": "65835c6006342b26ccb727ba2cb87b4550c45cdb6d69175a9ede5534de989c93",
".modelhub_state/routing_intelligence.json": "27c89641ad1b9184518ed0bbd8e8cc228c8cd6c089ac83dda09b03080e8e6426",
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
"ledger/submissions.jsonl": "b04c535f690908a7655f36df719d856a703bafa659d0baae375f95f7f706573e",
"outcomes/submissions.jsonl": "343e5246b450188d751488fb92c31996460cf7e0fa5b40593f621bd8587c5168"
"outcomes/submissions.jsonl": "a4101a15b1deed95c97b6809aa69469cc1f39c8a9cf07c5e1814d70ff9449b25"
},
"generation": 11140,
"phase": "cycle",
"generation": 11141,
"phase": "intent",
"schemaVersion": 1,
"updatedAt": "2026-09-21T03:28:37.965849+00:00",
"updatedAt": "2026-09-21T03:31:26.101343+00:00",
"writerId": "8b35139af6674067a339a670222d4b67"
}

5
outcomes/submissions.jsonl
View File

@@ -110,7 +110,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T08:15:14.695130+00:00", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608423891, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:45.139430+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730592", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T11:43:37.216638+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574489, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574577}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T03:43:18.853211+00:00", "targetGpu": "Vastai_va16", "taskId": "4733415", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T12:18:30.400502+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574577, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574577}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T04:15:09.998965+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4733756", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T14:59:28.333281+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22286993822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T06:54:09.304972+00:00", "targetGpu": "Vastai_va16", "taskId": "4735789", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T15:13:55.015976+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35620174949, "estimatedRequiredGiB": 39.84, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9345525760, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35648665467}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:10:09.840421+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4736014", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T15:30:59.418702+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35620174949, "estimatedRequiredGiB": 39.84, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9345525760, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35648665467}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:25:45.301380+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4736171", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-09T15:47:37.673636+00:00", "modelId": "Mungert/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "50b371e6c8f9d28c4f46314b835c0bfdf8660f3714d3c2804419c82f88e71ddb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 966342688, "estimatedRequiredGiB": 57.767, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 51688732063}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:39:28.588872+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4736314", "taskType": "text-generation", "verifyResult": null}
@@ -163,7 +162,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-11T18:34:19.116348+00:00", "modelId": "guaidao2/LFM2.5-2.6B-For-CTF", "modelProfile": {"architectures": [], "configFingerprint": "210478cd4aaac159760a821d912afadc8c24e731c59a89524484711a2c016d6a", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2874779040, "estimatedRequiredGiB": 11.734, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10499570876, "modelscopeLicense": null, "modelscopeParams": 2697198592, "modelscopeTags": ["library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10499570876}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:33.286927+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776571", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-11T18:34:19.116372+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26090095180, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:33.293196+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776566", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-11T23:52:34.207593+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 3443, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T15:45:34.084559+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4782449", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-11T23:52:34.207615+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T15:47:34.151696+00:00", "targetGpu": "Vastai_va16", "taskId": "4782467", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-12T00:09:40.009697+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 3443, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T16:03:11.891697+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4782663", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-12T00:09:40.009666+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T16:05:31.441883+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4782685", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-12T00:26:24.633017+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 3443, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T16:20:38.542601+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4782813", "taskType": "text-generation", "verifyResult": null}
@@ -320,8 +318,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T00:44:15.587025+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T16:34:57.059279+00:00", "targetGpu": "Vastai_va16", "taskId": "4919179", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T00:44:15.587034+00:00", "modelId": "hcnote/SparkMuse-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4453695184, "estimatedRequiredGiB": 4.989, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4463853848, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4114366080, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 4463853848}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T16:34:57.052651+00:00", "targetGpu": "Vastai_va16", "taskId": "4919176", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T00:44:15.587030+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T16:34:57.137322+00:00", "targetGpu": "Vastai_va16", "taskId": "4919178", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T00:44:15.587006+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T16:34:57.057055+00:00", "targetGpu": "Vastai_va16", "taskId": "4919175", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T00:44:15.587019+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7276346365, "estimatedRequiredGiB": 8.156, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7298158256, "modelscopeLicense": null, "modelscopeParams": 1959473664, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7298158256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T16:34:57.075622+00:00", "targetGpu": "Vastai_va16", "taskId": "4919177", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-18T00:44:15.586988+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "2081e784bf647d2735a87e674cde25dff30d7327eb04a4015607c2c9f9a8f0d9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T16:34:57.049175+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4919173", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T00:44:15.587040+00:00", "modelId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 52429250296, "estimatedRequiredGiB": 58.623, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe_text", "modelscopeFileSize": 52454809833, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26213016704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:expert-pruning", "custom_tag:code", "custom_tag:mtp", "custom_tag:ornith", "custom_tag:reap", "custom_tag:ream", "custom_tag:omnimergekit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 52454809833}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T16:34:57.068222+00:00", "targetGpu": "Biren_166m", "taskId": "4919174", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-18T00:55:47.967330+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7276346365, "estimatedRequiredGiB": 8.156, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7298158256, "modelscopeLicense": null, "modelscopeParams": 1959473664, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7298158256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T16:51:39.112864+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4919520", "taskType": "text-generation", "verifyResult": null}
@@ -628,7 +624,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.670610+00:00", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21855018733, "estimatedRequiredGiB": 24.461, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 21887495988, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6144703054, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21887495988}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:42.241690+00:00", "targetGpu": "Vastai_va16", "taskId": "4969986", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671140+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:42.247748+00:00", "targetGpu": "Vastai_va16", "taskId": "4969992", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671287+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663396475}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:42.240363+00:00", "targetGpu": "Vastai_va16", "taskId": "4969984", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.670516+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:42.245581+00:00", "targetGpu": "Vastai_va16", "taskId": "4969995", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.670877+00:00", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5254590634}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:42.242718+00:00", "targetGpu": "Vastai_va16", "taskId": "4969993", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.670774+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.622, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345693224, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345693224}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:48.957764+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969998", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.671075+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:48.962596+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970005", "taskType": "text-generation", "verifyResult": null}