state: generation 11141 (intent)
This commit is contained in:
@@ -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
|
||||
},
|
||||
|
||||
@@ -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,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -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
|
||||
}
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -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}
|
||||
|
||||
@@ -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"}
|
||||
|
||||
Reference in New Issue
Block a user