state: generation 5992 (cycle)

This commit is contained in:
2026-09-12 02:59:05 +00:00
parent da74f4fe1b
commit 54d1146595
11 changed files with 2176 additions and 2092 deletions

View File

@@ -1007,6 +1007,25 @@
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation"
},
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:nemotron_h": {
"architectureSignature": "model_type:nemotron_h",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-12T02:51:21+00:00",
"framework": "vllm_fix_tokenizer",
"latestFailureAt": "2026-09-12T02:51:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "nemotron_h",
"sourceModelIds": [
"nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4"
],
"sourceTaskIds": [
"4134178"
],
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation"
},
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
@@ -1326,9 +1345,9 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-12T02:55:53.615460+00:00",
"generatedAt": "2026-09-12T02:59:04.590587+00:00",
"summary": {
"activeBlockCount": 67,
"activeBlockCount": 68,
"byGpuFramework": {
"Ascend_910-b3|vllm": 8,
"Ascend_910-b4|vllm": 9,
@@ -1338,7 +1357,7 @@
"MetaX_c-500|vllm": 7,
"Mthreads_s4000|vllm": 7,
"Sunrise_pt-200-x1|vllm": 1,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 2,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 3,
"Vastai_va16|vllm": 12,
"Vastai_va16|vllm_fix_tokenizer": 2,
"hygon_k100-ai|vllm": 7,

View File

@@ -35,7 +35,7 @@
"2": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 430,
"listingErrors": 431,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 2,
"nextAccountIndex": 3,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-12T02:55:53.587554+00:00",
"updatedAt": "2026-09-12T02:59:04.560993+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T02:54:17.744485+00:00",
"generatedAt": "2026-09-12T02:57:05.481546+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T02:48:11.405538+00:00",
"lastSyncTime": "2026-09-12T02:48:11.158163+00:00",
"generatedAt": "2026-09-12T02:56:54.666019+00:00",
"lastSyncTime": "2026-09-12T02:56:54.384007+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1011,6 +1011,25 @@
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation"
},
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:nemotron_h": {
"architectureSignature": "model_type:nemotron_h",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-12T02:51:21+00:00",
"framework": "vllm_fix_tokenizer",
"latestFailureAt": "2026-09-12T02:51:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "nemotron_h",
"sourceModelIds": [
"nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4"
],
"sourceTaskIds": [
"4134178"
],
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation"
},
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
@@ -1331,7 +1350,7 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 67,
"activeBlockCount": 68,
"byGpuFramework": {
"Ascend_910-b3|vllm": 8,
"Ascend_910-b4|vllm": 9,
@@ -1341,7 +1360,7 @@
"MetaX_c-500|vllm": 7,
"Mthreads_s4000|vllm": 7,
"Sunrise_pt-200-x1|vllm": 1,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 2,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 3,
"Vastai_va16|vllm": 12,
"Vastai_va16|vllm_fix_tokenizer": 2,
"hygon_k100-ai|vllm": 7,
@@ -1482,18 +1501,18 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 37,
"attributableFailureCount": 38,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 37,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 33,
"framework_architecture_unsupported": 33,
"framework_architecture_unsupported": 34,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 2
},
"failureCount": 70,
"failureCount": 71,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1503,7 +1522,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 70,
"total": 71,
"unresolvedFailureCount": 33
},
"Biren_166m|unknown|text-generation": {
@@ -2082,17 +2101,17 @@
"unresolvedFailureCount": 33
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 41,
"attributableFailureCount": 42,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 41,
"decisionTotal": 42,
"failureBreakdown": {
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 4,
"platform_infrastructure": 2,
"tokenizer_compatibility": 38,
"参数/模板问题": 6
},
"failureCount": 49,
"failureCount": 50,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2102,22 +2121,22 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 49,
"total": 50,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 2
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2127,7 +2146,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 3
},
"Vastai_va16|unknown|text-generation": {
@@ -2356,30 +2375,30 @@
"unresolvedFailureCount": 862
},
"vllm": {
"attributableFailureCount": 246,
"attributableFailureCount": 248,
"decisionFailureRate": 0.988,
"decisionSuccessRate": 0.012,
"decisionTotal": 249,
"decisionTotal": 251,
"failureBreakdown": {
"ambiguous_runtime": 195,
"backend_operator": 33,
"framework_architecture_unsupported": 172,
"framework_architecture_unsupported": 173,
"memory_capacity": 6,
"model_load": 20,
"platform_infrastructure": 1,
"repository_structure": 5,
"runtime_memory": 6,
"tokenizer_compatibility": 4,
"tokenizer_compatibility": 5,
"参数/模板问题": 24
},
"failureCount": 466,
"failureCount": 468,
"failureRate": 0.9936,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0064,
"total": 469,
"total": 471,
"unresolvedFailureCount": 219
},
"vllm-mlu": {
@@ -2442,26 +2461,26 @@
"unresolvedFailureCount": 4
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 44,
"attributableFailureCount": 45,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"decisionTotal": 45,
"failureBreakdown": {
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 5,
"framework_architecture_unsupported": 6,
"model_load": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 38,
"参数/模板问题": 7
},
"failureCount": 89,
"failureCount": 90,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 89,
"total": 90,
"unresolvedFailureCount": 43
},
"vllm_tokenizer_patch": {
@@ -2483,7 +2502,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T02:48:11.401315+00:00",
"generatedAt": "2026-09-12T02:56:54.660525+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2509,13 +2528,13 @@
"unresolvedFailureCount": 63
},
"Ascend_910-b4": {
"attributableFailureCount": 38,
"decisionFailureRate": 0.95,
"decisionSuccessRate": 0.05,
"decisionTotal": 40,
"attributableFailureCount": 39,
"decisionFailureRate": 0.9512,
"decisionSuccessRate": 0.0488,
"decisionTotal": 41,
"failureBreakdown": {
"ambiguous_runtime": 34,
"framework_architecture_unsupported": 33,
"framework_architecture_unsupported": 34,
"memory_capacity": 1,
"model_load": 1,
"repository_structure": 1,
@@ -2523,14 +2542,14 @@
"参数/模板问题": 12,
"验证失败": 175
},
"failureCount": 259,
"failureRate": 0.9923,
"failureCount": 260,
"failureRate": 0.9924,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0077,
"total": 261,
"successRate": 0.0076,
"total": 262,
"unresolvedFailureCount": 221
},
"Biren_166m": {
@@ -2741,26 +2760,26 @@
"unresolvedFailureCount": 77
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 43,
"decisionFailureRate": 0.9773,
"decisionSuccessRate": 0.0227,
"decisionTotal": 44,
"attributableFailureCount": 45,
"decisionFailureRate": 0.9783,
"decisionSuccessRate": 0.0217,
"decisionTotal": 46,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 4,
"framework_architecture_unsupported": 5,
"platform_infrastructure": 3,
"tokenizer_compatibility": 39,
"tokenizer_compatibility": 40,
"参数/模板问题": 9,
"验证失败": 32
},
"failureCount": 88,
"failureRate": 0.9888,
"failureCount": 90,
"failureRate": 0.989,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 1,
"successRate": 0.0112,
"total": 89,
"successRate": 0.011,
"total": 91,
"unresolvedFailureCount": 42
},
"Vastai_va16": {
@@ -3976,6 +3995,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|hrm_text|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -4204,7 +4246,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T15:48:17.745912+00:00",
"lastTerminalAt": "2026-09-12T02:56:54.384007+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4551,22 +4593,22 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 18,
"consecutiveFailures": 18,
"attributableFailureCount": 17,
"consecutiveFailures": 17,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 18,
"decisionTotal": 17,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"platform_infrastructure": 2,
"tokenizer_compatibility": 16
"tokenizer_compatibility": 15
},
"failureCount": 20,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-10T11:01:21+00:00",
"lastTerminalAt": "2026-09-12T02:48:11.158114+00:00",
"lastTerminalAt": "2026-09-12T02:56:54.383989+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
@@ -4574,7 +4616,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 20,
"total": 19,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -6928,6 +6970,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|llama|compressed-tensors|30": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|hrm_text|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -7121,41 +7187,40 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1677,
"totalRecords": 1764,
"terminalRecords": 1680,
"totalRecords": 1767,
"totals": {
"attributableFailureCount": 449,
"decisionFailureRate": 0.8891,
"decisionSuccessRate": 0.1109,
"decisionTotal": 505,
"attributableFailureCount": 452,
"decisionFailureRate": 0.8898,
"decisionSuccessRate": 0.1102,
"decisionTotal": 508,
"failureBreakdown": {
"ambiguous_runtime": 394,
"backend_operator": 40,
"framework_architecture_unsupported": 278,
"framework_architecture_unsupported": 280,
"memory_capacity": 11,
"model_load": 64,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
"tokenizer_compatibility": 45,
"tokenizer_compatibility": 46,
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1621,
"failureRate": 0.9666,
"failureCount": 1624,
"failureRate": 0.9667,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 56,
"successRate": 0.0334,
"total": 1677,
"successRate": 0.0333,
"total": 1680,
"unresolvedFailureCount": 1168
},
"warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -7164,6 +7229,7 @@
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7179,11 +7245,12 @@
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 MetaX_c-500|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1764,
"summarizedRecords": 1767,
"version": 1
}

View File

@@ -14,13 +14,13 @@
100
],
"accounts": 12,
"activeScanned": 1055,
"activeScanned": 1054,
"ageCleanupMode": "admission_only",
"agePolicySkipped": {
"cleanupDisabled": true,
"reason": "admission_only"
},
"architectureBlockCount": 67,
"architectureBlockCount": 68,
"architectureFrameworkCatalog": {
"ascend_910-b3|text-generation": [
"llamacpp",
@@ -98,10 +98,10 @@
"architectureOnly": true,
"architecturePolicySkipped": {
"frameworkCatalogUnknown": 87,
"frameworkContextUnknown": 330,
"frameworkContextUnknown": 329,
"modelArchitectureUnknown": 150,
"noMatchingBlock": 720,
"partiallyBlockedFrameworkSet": 98,
"noMatchingBlock": 718,
"partiallyBlockedFrameworkSet": 99,
"runningMatchedProtected": 0,
"submissionContextMismatch": 0,
"submissionContextUnknown": 0

View File

@@ -1,3 +1,5 @@
{"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", "framework": "vllm", "lastSyncTime": "2026-09-12T02:56:54.384007+00:00", "modelId": "amd/Qwen2.5-7B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:53:23+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079108", "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", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T02:56:54.383989+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:51:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4134178", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T02:48:11.158114+00:00", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:43:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458009", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T02:39:29.219599+00:00", "modelId": "RedHatAI/Qwen2.5-3B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:39:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4100876", "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", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mellum"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T02:39:29.219629+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Thinking", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:35:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4152611", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T13:16:14.206275+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T12:57:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4107036", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T12:42:19.103212+00:00", "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T12:21:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4133653", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T12:42:19.103221+00:00", "modelId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T12:19:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4107014", "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", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T12:42:19.103172+00:00", "modelId": "iic/UEmbed-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T12:15:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4152744", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T12:11:42.795229+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T12:11:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4101032", "taskType": "text-generation", "verifyResult": -1}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff