state: generation 5337 (cycle)
This commit is contained in:
@@ -1309,7 +1309,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T19:55:50.534207+00:00",
|
||||
"generatedAt": "2026-09-10T19:59:08.994397+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 66,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -83,7 +83,7 @@
|
||||
"8": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 379,
|
||||
"listingErrors": 380,
|
||||
"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": 8,
|
||||
"nextAccountIndex": 9,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-10T19:55:50.510294+00:00",
|
||||
"updatedAt": "2026-09-10T19:59:08.968918+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-10T19:53:39.805662+00:00",
|
||||
"generatedAt": "2026-09-10T19:56:58.303064+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T19:48:10.294794+00:00",
|
||||
"lastSyncTime": "2026-09-10T19:48:09.995356+00:00",
|
||||
"generatedAt": "2026-09-10T19:56:52.084081+00:00",
|
||||
"lastSyncTime": "2026-09-10T19:56:51.309700+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1794,7 +1794,7 @@
|
||||
"decisionSuccessRate": 0.1163,
|
||||
"decisionTotal": 86,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 17,
|
||||
"ambiguous_runtime": 18,
|
||||
"framework_architecture_unsupported": 48,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 27,
|
||||
@@ -1802,18 +1802,18 @@
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 143,
|
||||
"failureRate": 0.9346,
|
||||
"failureCount": 144,
|
||||
"failureRate": 0.9351,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 10,
|
||||
"successRate": 0.0654,
|
||||
"successRate": 0.0649,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 153,
|
||||
"unresolvedFailureCount": 66
|
||||
"total": 154,
|
||||
"unresolvedFailureCount": 67
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -2142,12 +2142,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 44,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 58,
|
||||
"ambiguous_runtime": 59,
|
||||
"framework_architecture_unsupported": 38,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 5
|
||||
},
|
||||
"failureCount": 102,
|
||||
"failureCount": 103,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -2157,8 +2157,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation",
|
||||
"total": 102,
|
||||
"unresolvedFailureCount": 58
|
||||
"total": 103,
|
||||
"unresolvedFailureCount": 59
|
||||
},
|
||||
"hygon_k100-ai|llamacpp|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -2295,7 +2295,7 @@
|
||||
"decisionSuccessRate": 0.2697,
|
||||
"decisionTotal": 178,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 123,
|
||||
"ambiguous_runtime": 124,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 89,
|
||||
"memory_capacity": 5,
|
||||
@@ -2305,15 +2305,15 @@
|
||||
"参数/模板问题": 56,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 983,
|
||||
"failureRate": 0.9534,
|
||||
"failureCount": 984,
|
||||
"failureRate": 0.9535,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 48,
|
||||
"successRate": 0.0466,
|
||||
"total": 1031,
|
||||
"unresolvedFailureCount": 852
|
||||
"successRate": 0.0465,
|
||||
"total": 1032,
|
||||
"unresolvedFailureCount": 853
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 240,
|
||||
@@ -2321,7 +2321,7 @@
|
||||
"decisionSuccessRate": 0.0083,
|
||||
"decisionTotal": 242,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 185,
|
||||
"ambiguous_runtime": 186,
|
||||
"backend_operator": 33,
|
||||
"framework_architecture_unsupported": 169,
|
||||
"memory_capacity": 6,
|
||||
@@ -2332,15 +2332,15 @@
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 24
|
||||
},
|
||||
"failureCount": 450,
|
||||
"failureCount": 451,
|
||||
"failureRate": 0.9956,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0044,
|
||||
"total": 452,
|
||||
"unresolvedFailureCount": 209
|
||||
"total": 453,
|
||||
"unresolvedFailureCount": 210
|
||||
},
|
||||
"vllm-mlu": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -2443,7 +2443,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T19:48:10.290792+00:00",
|
||||
"generatedAt": "2026-09-10T19:56:52.079960+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2611,7 +2611,7 @@
|
||||
"decisionSuccessRate": 0.1163,
|
||||
"decisionTotal": 86,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 17,
|
||||
"ambiguous_runtime": 18,
|
||||
"framework_architecture_unsupported": 48,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 27,
|
||||
@@ -2619,15 +2619,15 @@
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 143,
|
||||
"failureRate": 0.9346,
|
||||
"failureCount": 144,
|
||||
"failureRate": 0.9351,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 10,
|
||||
"successRate": 0.0654,
|
||||
"total": 153,
|
||||
"unresolvedFailureCount": 66
|
||||
"successRate": 0.0649,
|
||||
"total": 154,
|
||||
"unresolvedFailureCount": 67
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -2729,22 +2729,22 @@
|
||||
"decisionSuccessRate": 0.2167,
|
||||
"decisionTotal": 60,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 60,
|
||||
"ambiguous_runtime": 61,
|
||||
"framework_architecture_unsupported": 40,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 6,
|
||||
"参数/模板问题": 13,
|
||||
"验证失败": 130
|
||||
},
|
||||
"failureCount": 250,
|
||||
"failureRate": 0.9506,
|
||||
"failureCount": 251,
|
||||
"failureRate": 0.9508,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 13,
|
||||
"successRate": 0.0494,
|
||||
"total": 263,
|
||||
"unresolvedFailureCount": 203
|
||||
"successRate": 0.0492,
|
||||
"total": 264,
|
||||
"unresolvedFailureCount": 204
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"attributableFailureCount": 39,
|
||||
@@ -4163,18 +4163,17 @@
|
||||
"unresolvedFailureCount": 14
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"参数/模板问题": 1
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 6,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4186,8 +4185,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 4
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm|text-generation": {
|
||||
"attributableFailureCount": 3,
|
||||
@@ -4271,28 +4270,29 @@
|
||||
"attributableFailureCount": 17,
|
||||
"consecutiveFailures": 9,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.8947,
|
||||
"decisionSuccessRate": 0.1053,
|
||||
"decisionTotal": 19,
|
||||
"decisionFailureRate": 0.9444,
|
||||
"decisionSuccessRate": 0.0556,
|
||||
"decisionTotal": 18,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 8,
|
||||
"model_load": 9,
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 18,
|
||||
"failureRate": 0.9,
|
||||
"failureCount": 19,
|
||||
"failureRate": 0.95,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
|
||||
"lastTerminalAt": "2026-09-10T19:38:05.602511+00:00",
|
||||
"lastTerminalAt": "2026-09-10T19:56:51.309700+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 2,
|
||||
"successRate": 0.1,
|
||||
"successCount": 1,
|
||||
"successRate": 0.05,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 0
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -4539,7 +4539,7 @@
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T19:48:09.995356+00:00",
|
||||
"lastTerminalAt": "2026-09-10T19:56:51.309666+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4656,31 +4656,6 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_mtp|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-mlu",
|
||||
"lastTerminalAt": "2026-09-08T18:40:55.416623+00:00",
|
||||
"modelType": "qwen3_5_mtp",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_moe|eschamoe": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
@@ -7020,15 +6995,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1628,
|
||||
"totalRecords": 1715,
|
||||
"terminalRecords": 1630,
|
||||
"totalRecords": 1717,
|
||||
"totals": {
|
||||
"attributableFailureCount": 425,
|
||||
"decisionFailureRate": 0.891,
|
||||
"decisionSuccessRate": 0.109,
|
||||
"decisionTotal": 477,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 376,
|
||||
"ambiguous_runtime": 378,
|
||||
"backend_operator": 40,
|
||||
"framework_architecture_unsupported": 273,
|
||||
"memory_capacity": 11,
|
||||
@@ -7040,31 +7015,30 @@
|
||||
"参数/模板问题": 98,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1576,
|
||||
"failureCount": 1578,
|
||||
"failureRate": 0.9681,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 52,
|
||||
"successRate": 0.0319,
|
||||
"total": 1628,
|
||||
"unresolvedFailureCount": 1147
|
||||
"total": 1630,
|
||||
"unresolvedFailureCount": 1149
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 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。",
|
||||
"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 MetaX_c-500 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 Iluvatar_bi-150 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 Cambricon_mlu-370-x8 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 Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x8 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。",
|
||||
"组合 Iluvatar_mrv-100|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 Cambricon_mlu-370-x4|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 Mthreads_s4000|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 Cambricon_mlu-370-x8|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 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。",
|
||||
@@ -7079,10 +7053,11 @@
|
||||
"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 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 Vastai_va16|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 Cambricon_mlu-370-x4|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 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。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1715,
|
||||
"summarizedRecords": 1717,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,5 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T19:56:51.309666+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:49:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477723", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T19:56:51.309700+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:49:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523214", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T19:48:09.995356+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:45:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477833", "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_mtp"], "framework": "", "lastSyncTime": "2026-09-10T19:38:05.602511+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-8bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332704", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T19:27:42.923434+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:25:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523215", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -296,5 +298,3 @@
|
||||
{"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": ["nemotron_h"], "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T20:33:46.399743+00:00", "modelId": "nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18974813860, "estimatedRequiredGiB": 21.229, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 18995666906, "modelscopeLicense": "other", "modelscopeParams": 15524066944, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18995666906}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:11.598902+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712818", "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": "2026-09-08T20:33:46.399718+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3403624536, "estimatedRequiredGiB": 3.828, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 3425449433, "modelscopeLicense": "llama2", "modelscopeParams": 3204165888, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3425449433}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:11.594968+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712814", "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": "2026-09-09T01:56:43.203825+00:00", "modelId": "RedHatAI/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615358, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615358}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:11.593738+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712817", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T04:17:40.427917+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.589203+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712819", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_mtp"], "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T18:40:55.416623+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 238933307, "estimatedRequiredGiB": 0.297, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 265664321, "modelscopeLicense": "apache-2.0", "modelscopeParams": 106194432, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:nvfp4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 265664321}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:11.587867+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712816", "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
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "f166d05575ba6eb454b216ff03a6a45f6e0f44f7cddc6576c38a7bea2f71ce93",
|
||||
".modelhub_state/architecture_history_backfill.json": "47ebd9041ff0b24891bd10545ac4fff866f28e83fa2525f4300b5210ecdb35ed",
|
||||
".modelhub_state/market_intelligence.json": "a6aad0d9b9e17b2f04a5a61c7ec5ae529b7abb3902df59ba464f3059bf1c8fa1",
|
||||
".modelhub_state/official_capabilities.json": "6fc9f797c025b8e302af630944b4e0f990b280868d4de79c6549d13acf1b679f",
|
||||
".modelhub_state/outcome_checkpoint.json": "e3cc11c7b5bd493198a0cf07cf68829a57a6b59822f64bc50b7170af0df0fc41",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "2c59340318728911d4b6b19f07c977f1f96bce2a863d262c00c60e26c53c01dc",
|
||||
".modelhub_state/architecture_history_backfill.json": "90b78e40acb591e4418bef6a8a9f7cce8f4db58ca2651e30a12d4e192e434240",
|
||||
".modelhub_state/market_intelligence.json": "a0ae1fbd8497a1f36d5718a4ab8bc1108dcb9d7b07c71452f2114ccac7119203",
|
||||
".modelhub_state/official_capabilities.json": "292f182f2d7591de0727a734868377d41ac1af6ceefe891c492b31b8a4d30f31",
|
||||
".modelhub_state/outcome_checkpoint.json": "fb513b4b42096d4f6b71d6395c2f57d40eba38dfd5ca4b9132611e1e6c485b00",
|
||||
".modelhub_state/queue_cleanup_latest.json": "c4c0c2f745124fbabf68b2aa082c5aeee0f45dbb41d40369e8064e674a33adbe",
|
||||
".modelhub_state/recent_outcomes.jsonl": "e6fe1b7782ab31a174f8f4376604b7c9183fa77c195694c2800b7217efb9c2de",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "f648d32ffa4d7ccc0863d5f18a53371ab301ee7cf04704727cece228139aee08",
|
||||
".modelhub_state/recovery_intents.jsonl": "3ef67e78da4dfb5a69d57c2a061e9165577a3fcb019500eeea6a7dd6dde383b4",
|
||||
".modelhub_state/recent_outcomes.jsonl": "9b9949ffe30122c53d85c1ea8e2870f413a5231b464f98f96658b5a7c1178177",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "a51fc3400b2a042b8d357116894b439c277db610a454f52646ed8aea44fe48d8",
|
||||
".modelhub_state/recovery_intents.jsonl": "78208fc611b8fe78f1cd53c544d4f8fd2cf7ca31142d5c6ecd2d6ad467518d61",
|
||||
".modelhub_state/routing_intelligence.json": "12b4c1be75fdc09d4e2562be20fdbdde456a6ff5edbfffb05bdea8b0984b2b06",
|
||||
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
|
||||
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
|
||||
"ledger/submissions.jsonl": "ee14dd31e9fdc4bbd6920091a841528560313233bd6a6a3755b5c6e38ceb873b",
|
||||
"outcomes/submissions.jsonl": "ec945eb0ce93dee58d9f01d5ee1b1ce0fd0ccb9bd1ed487b2d4fb314f64d306d"
|
||||
},
|
||||
"generation": 5336,
|
||||
"generation": 5337,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-10T19:55:50.655182+00:00",
|
||||
"updatedAt": "2026-09-10T19:59:09.628756+00:00",
|
||||
"writerId": "18252d8a8ef94333abd55823b2d81c42"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user