state: generation 5143 (cycle)
This commit is contained in:
@@ -1313,7 +1313,7 @@
|
|||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-09-10T11:39:51.888215+00:00",
|
"generatedAt": "2026-09-10T11:42:29.004979+00:00",
|
||||||
"summary": {
|
"summary": {
|
||||||
"activeBlockCount": 66,
|
"activeBlockCount": 66,
|
||||||
"byGpuFramework": {
|
"byGpuFramework": {
|
||||||
|
|||||||
@@ -75,7 +75,7 @@
|
|||||||
"7": {
|
"7": {
|
||||||
"complete": false,
|
"complete": false,
|
||||||
"lastError": "ModelHubAPIError: 系统错误",
|
"lastError": "ModelHubAPIError: 系统错误",
|
||||||
"listingErrors": 365,
|
"listingErrors": 366,
|
||||||
"nextPage": 1,
|
"nextPage": 1,
|
||||||
"recordsScanned": 0,
|
"recordsScanned": 0,
|
||||||
"uniqueRecords": 0
|
"uniqueRecords": 0
|
||||||
@@ -102,12 +102,12 @@
|
|||||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||||
"failureLogsInspected": 0,
|
"failureLogsInspected": 0,
|
||||||
"mode": "incremental_decision_only",
|
"mode": "incremental_decision_only",
|
||||||
"nextAccountIndex": 7,
|
"nextAccountIndex": 8,
|
||||||
"recordsScanned": 0,
|
"recordsScanned": 0,
|
||||||
"seenTaskIds": [],
|
"seenTaskIds": [],
|
||||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||||
"terminalRecords": 0,
|
"terminalRecords": 0,
|
||||||
"uniqueRecords": 0,
|
"uniqueRecords": 0,
|
||||||
"updatedAt": "2026-09-10T11:39:51.864460+00:00",
|
"updatedAt": "2026-09-10T11:42:28.980295+00:00",
|
||||||
"version": 1
|
"version": 1
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -416,7 +416,7 @@
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
"frameworkUpdatedAt": null,
|
"frameworkUpdatedAt": null,
|
||||||
"generatedAt": "2026-09-10T11:37:30.033164+00:00",
|
"generatedAt": "2026-09-10T11:40:59.915242+00:00",
|
||||||
"gpuStats": {
|
"gpuStats": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"available": true,
|
"available": true,
|
||||||
|
|||||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"generatedAt": "2026-09-10T11:31:55.552238+00:00",
|
"generatedAt": "2026-09-10T11:40:52.921299+00:00",
|
||||||
"lastSyncTime": "2026-09-10T11:31:55.305639+00:00",
|
"lastSyncTime": "2026-09-10T11:40:52.603367+00:00",
|
||||||
"recentLimit": 300,
|
"recentLimit": 300,
|
||||||
"report": {
|
"report": {
|
||||||
"architectureCompatibilityBlocks": {
|
"architectureCompatibilityBlocks": {
|
||||||
@@ -1386,12 +1386,12 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 26,
|
"decisionTotal": 26,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 23,
|
"ambiguous_runtime": 26,
|
||||||
"framework_architecture_unsupported": 24,
|
"framework_architecture_unsupported": 24,
|
||||||
"memory_capacity": 1,
|
"memory_capacity": 1,
|
||||||
"tokenizer_compatibility": 1
|
"tokenizer_compatibility": 1
|
||||||
},
|
},
|
||||||
"failureCount": 49,
|
"failureCount": 52,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm",
|
"framework": "vllm",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
@@ -1401,8 +1401,8 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Ascend_910-b3",
|
"targetGpu": "Ascend_910-b3",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 49,
|
"total": 52,
|
||||||
"unresolvedFailureCount": 23
|
"unresolvedFailureCount": 26
|
||||||
},
|
},
|
||||||
"Ascend_910-b4|llamacpp|text-generation": {
|
"Ascend_910-b4|llamacpp|text-generation": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 1,
|
||||||
@@ -2321,7 +2321,7 @@
|
|||||||
"decisionSuccessRate": 0.0042,
|
"decisionSuccessRate": 0.0042,
|
||||||
"decisionTotal": 236,
|
"decisionTotal": 236,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 163,
|
"ambiguous_runtime": 166,
|
||||||
"backend_operator": 29,
|
"backend_operator": 29,
|
||||||
"framework_architecture_unsupported": 169,
|
"framework_architecture_unsupported": 169,
|
||||||
"memory_capacity": 6,
|
"memory_capacity": 6,
|
||||||
@@ -2332,15 +2332,15 @@
|
|||||||
"tokenizer_compatibility": 3,
|
"tokenizer_compatibility": 3,
|
||||||
"参数/模板问题": 21
|
"参数/模板问题": 21
|
||||||
},
|
},
|
||||||
"failureCount": 420,
|
"failureCount": 423,
|
||||||
"failureRate": 0.9976,
|
"failureRate": 0.9976,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 1,
|
"platformFailureCount": 1,
|
||||||
"successCount": 1,
|
"successCount": 1,
|
||||||
"successRate": 0.0024,
|
"successRate": 0.0024,
|
||||||
"total": 421,
|
"total": 424,
|
||||||
"unresolvedFailureCount": 184
|
"unresolvedFailureCount": 187
|
||||||
},
|
},
|
||||||
"vllm-mlu": {
|
"vllm-mlu": {
|
||||||
"attributableFailureCount": 7,
|
"attributableFailureCount": 7,
|
||||||
@@ -2443,7 +2443,7 @@
|
|||||||
"unresolvedFailureCount": 1
|
"unresolvedFailureCount": 1
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-09-10T11:31:55.546929+00:00",
|
"generatedAt": "2026-09-10T11:40:52.916454+00:00",
|
||||||
"gpuSummaries": {
|
"gpuSummaries": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"attributableFailureCount": 26,
|
"attributableFailureCount": 26,
|
||||||
@@ -2451,22 +2451,22 @@
|
|||||||
"decisionSuccessRate": 0.037,
|
"decisionSuccessRate": 0.037,
|
||||||
"decisionTotal": 27,
|
"decisionTotal": 27,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 23,
|
"ambiguous_runtime": 26,
|
||||||
"framework_architecture_unsupported": 24,
|
"framework_architecture_unsupported": 24,
|
||||||
"memory_capacity": 1,
|
"memory_capacity": 1,
|
||||||
"tokenizer_compatibility": 1,
|
"tokenizer_compatibility": 1,
|
||||||
"参数/模板问题": 8,
|
"参数/模板问题": 8,
|
||||||
"验证失败": 27
|
"验证失败": 27
|
||||||
},
|
},
|
||||||
"failureCount": 84,
|
"failureCount": 87,
|
||||||
"failureRate": 0.9882,
|
"failureRate": 0.9886,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 0,
|
"platformFailureCount": 0,
|
||||||
"successCount": 1,
|
"successCount": 1,
|
||||||
"successRate": 0.0118,
|
"successRate": 0.0114,
|
||||||
"total": 85,
|
"total": 88,
|
||||||
"unresolvedFailureCount": 58
|
"unresolvedFailureCount": 61
|
||||||
},
|
},
|
||||||
"Ascend_910-b4": {
|
"Ascend_910-b4": {
|
||||||
"attributableFailureCount": 38,
|
"attributableFailureCount": 38,
|
||||||
@@ -3983,21 +3983,21 @@
|
|||||||
},
|
},
|
||||||
"recentCombinationStats": {
|
"recentCombinationStats": {
|
||||||
"Ascend_910-b3|vllm|text-generation": {
|
"Ascend_910-b3|vllm|text-generation": {
|
||||||
"attributableFailureCount": 2,
|
"attributableFailureCount": 1,
|
||||||
"consecutiveFailures": 2,
|
"consecutiveFailures": 1,
|
||||||
"consecutivePlatformFailures": 0,
|
"consecutivePlatformFailures": 0,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 2,
|
"decisionTotal": 1,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 17,
|
"ambiguous_runtime": 19,
|
||||||
"framework_architecture_unsupported": 2
|
"framework_architecture_unsupported": 1
|
||||||
},
|
},
|
||||||
"failureCount": 19,
|
"failureCount": 20,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm",
|
"framework": "vllm",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
"lastTerminalAt": "2026-09-10T09:20:50.207436+00:00",
|
"lastTerminalAt": "2026-09-10T11:40:52.603333+00:00",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 0,
|
"platformFailureCount": 0,
|
||||||
@@ -4005,8 +4005,8 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Ascend_910-b3",
|
"targetGpu": "Ascend_910-b3",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 19,
|
"total": 20,
|
||||||
"unresolvedFailureCount": 17
|
"unresolvedFailureCount": 19
|
||||||
},
|
},
|
||||||
"Ascend_910-b4|llamacpp|text-generation": {
|
"Ascend_910-b4|llamacpp|text-generation": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 1,
|
||||||
@@ -4202,9 +4202,9 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 0,
|
"decisionTotal": 0,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 2
|
"ambiguous_runtime": 1
|
||||||
},
|
},
|
||||||
"failureCount": 2,
|
"failureCount": 1,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "transformers",
|
"framework": "transformers",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
@@ -4216,8 +4216,8 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Iluvatar_bi-100",
|
"targetGpu": "Iluvatar_bi-100",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 2,
|
"total": 1,
|
||||||
"unresolvedFailureCount": 2
|
"unresolvedFailureCount": 1
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150|vllm|text-generation": {
|
"Iluvatar_bi-150|vllm|text-generation": {
|
||||||
"attributableFailureCount": 4,
|
"attributableFailureCount": 4,
|
||||||
@@ -4281,9 +4281,9 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 0,
|
"decisionTotal": 0,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 6
|
"ambiguous_runtime": 5
|
||||||
},
|
},
|
||||||
"failureCount": 6,
|
"failureCount": 5,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "unknown",
|
"framework": "unknown",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
@@ -4295,8 +4295,8 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Kunlunxin_p-800",
|
"targetGpu": "Kunlunxin_p-800",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 6,
|
"total": 5,
|
||||||
"unresolvedFailureCount": 6
|
"unresolvedFailureCount": 5
|
||||||
},
|
},
|
||||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
|
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
|
||||||
"attributableFailureCount": 0,
|
"attributableFailureCount": 0,
|
||||||
@@ -7002,15 +7002,15 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"terminalRecords": 1565,
|
"terminalRecords": 1568,
|
||||||
"totalRecords": 1652,
|
"totalRecords": 1655,
|
||||||
"totals": {
|
"totals": {
|
||||||
"attributableFailureCount": 409,
|
"attributableFailureCount": 409,
|
||||||
"decisionFailureRate": 0.8891,
|
"decisionFailureRate": 0.8891,
|
||||||
"decisionSuccessRate": 0.1109,
|
"decisionSuccessRate": 0.1109,
|
||||||
"decisionTotal": 460,
|
"decisionTotal": 460,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 334,
|
"ambiguous_runtime": 337,
|
||||||
"backend_operator": 34,
|
"backend_operator": 34,
|
||||||
"framework_architecture_unsupported": 271,
|
"framework_architecture_unsupported": 271,
|
||||||
"memory_capacity": 11,
|
"memory_capacity": 11,
|
||||||
@@ -7022,21 +7022,21 @@
|
|||||||
"参数/模板问题": 95,
|
"参数/模板问题": 95,
|
||||||
"验证失败": 673
|
"验证失败": 673
|
||||||
},
|
},
|
||||||
"failureCount": 1514,
|
"failureCount": 1517,
|
||||||
"failureRate": 0.9674,
|
"failureRate": 0.9675,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 3,
|
"platformFailureCount": 3,
|
||||||
"successCount": 51,
|
"successCount": 51,
|
||||||
"successRate": 0.0326,
|
"successRate": 0.0325,
|
||||||
"total": 1565,
|
"total": 1568,
|
||||||
"unresolvedFailureCount": 1102
|
"unresolvedFailureCount": 1105
|
||||||
},
|
},
|
||||||
"warnings": [
|
"warnings": [
|
||||||
"GPU Cambricon_mlu-370-x8 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 Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
|
"GPU Ascend_910-b3 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 Iluvatar_mrv-100 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。",
|
||||||
"GPU Ascend_910-b4 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 Vastai_va16 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 MetaX_c-500 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。",
|
||||||
@@ -7044,7 +7044,7 @@
|
|||||||
"GPU hygon_k100-ai 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 Cambricon_mlu-370-x4 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 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 Iluvatar_bi-150 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 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-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 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 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 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。",
|
||||||
@@ -7065,6 +7065,6 @@
|
|||||||
]
|
]
|
||||||
},
|
},
|
||||||
"storageMode": "decision_state_only",
|
"storageMode": "decision_state_only",
|
||||||
"summarizedRecords": 1652,
|
"summarizedRecords": 1655,
|
||||||
"version": 1
|
"version": 1
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -1,3 +1,6 @@
|
|||||||
|
{"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": "2026-09-10T11:40:52.603333+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:39:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505113", "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": "2026-09-10T11:40:52.603356+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:39:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505112", "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": "2026-09-10T11:40:52.603367+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:37:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505111", "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": "2026-09-10T11:31:55.305639+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:25:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471913", "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": "2026-09-10T11:31:55.305639+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:25:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471913", "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": "2026-09-10T11:14:50.402520+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4134179", "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": "2026-09-10T11:14:50.402520+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4134179", "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": "2026-09-10T11:06:41.315652+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:05:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4134097", "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": "2026-09-10T11:06:41.315652+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:05:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4134097", "taskType": "text-generation", "verifyResult": -1}
|
||||||
@@ -295,6 +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": "", "lastSyncTime": "2026-09-07T23:25:25.308783+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:19:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4133677", "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": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-07T23:25:25.308783+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:19:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4133677", "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": "2026-09-07T23:16:42.601369+00:00", "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:15:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332994", "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": "2026-09-07T23:16:42.601369+00:00", "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:15:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332994", "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": "2026-09-07T23:16:42.601390+00:00", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4083483", "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": "2026-09-07T23:16:42.601390+00:00", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4083483", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "", "lastSyncTime": "2026-09-07T23:07:55.698411+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:07:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4271662", "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": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-07T22:59:07.700197+00:00", "modelId": "nightmedia/Qwen3-4B-Element8-Eva-Heretic-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T22:57:21+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4080072", "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": "2026-09-07T22:32:11.428265+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T22:31:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4483787", "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",
|
"agentVersion": "2026.09.04.4",
|
||||||
"checksums": {
|
"checksums": {
|
||||||
".modelhub_state/architecture_compatibility_blacklist.json": "13414f4c0d5fc0c7fa9b112be97e9a9b37dee95a5a33e68f5309e5c6374ba52f",
|
".modelhub_state/architecture_compatibility_blacklist.json": "bbce9b3e1e3dc95f6f3dc8c39701187ee98ed7fd3adbc409faeda4d73e3614f2",
|
||||||
".modelhub_state/architecture_history_backfill.json": "6789eac1f863b06cc885351f350966c37b9cd50ff644c165c8fc7551ac3c1dd2",
|
".modelhub_state/architecture_history_backfill.json": "ecd2057bbabe798f3d9c22679acc46ba64532ccdaffc18d961852247ad76cfe9",
|
||||||
".modelhub_state/market_intelligence.json": "2735f22c21a6a483cb4475addf8b2041d6d568c3de1564df2041232b6c1d444a",
|
".modelhub_state/market_intelligence.json": "4248f36f006902676a6fc38335c6ab021fdd713745699e9746954df6dbff55b5",
|
||||||
".modelhub_state/official_capabilities.json": "50d37e092d65250fecc54ab7faf855e1ec822a7844db0f87958039d24ca65378",
|
".modelhub_state/official_capabilities.json": "d70ed1939d95f1a4626a10b45d49986e373ca8e5595cfffd16500fd6c54cf08a",
|
||||||
".modelhub_state/outcome_checkpoint.json": "33a7744fb500a51a0c8f346c2049cbc0df1746e93433ffcfe06e10e16cc0c274",
|
".modelhub_state/outcome_checkpoint.json": "3f40fbd199c8837295f6115a33da6d87af6e23d76c4b7d3949f8aba7c0067e82",
|
||||||
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
|
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
|
||||||
".modelhub_state/recent_outcomes.jsonl": "2cb2e7472b0438479ea47741a777fc7df816050bf4a9a7ffc011c3936b86388a",
|
".modelhub_state/recent_outcomes.jsonl": "9c76c675711d73c096bf81946bd4da6c45a966e8714578e5904f9f8e3e999694",
|
||||||
".modelhub_state/recovery_active_tasks.jsonl": "c51700b33973a26163e0510b5d2f13ffa937c5e0dee9a8da4fb8a9e5479f7d19",
|
".modelhub_state/recovery_active_tasks.jsonl": "f943a1254b5aa8966d0fcd18531de3065c2e6d3bc53afca50621a9320726e14f",
|
||||||
".modelhub_state/recovery_intents.jsonl": "1d6f497100c32d3e4ba565f5124bbc4f0bd2d980ce902428ed2a0979e92d5dcd",
|
".modelhub_state/recovery_intents.jsonl": "549bd73ef02af451a46894496547fc2c1bbd90b6329feef562a80fdc5c75e5b5",
|
||||||
".modelhub_state/routing_intelligence.json": "f36cfaf9f9ff191164b0ce0a73a3ce4bbc3a2dc4589f252d583e33b427807fc0",
|
".modelhub_state/routing_intelligence.json": "f36cfaf9f9ff191164b0ce0a73a3ce4bbc3a2dc4589f252d583e33b427807fc0",
|
||||||
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
|
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
|
||||||
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
|
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
|
||||||
"ledger/submissions.jsonl": "8a621da5637d481c7de4b4e3375f2a68cbdabf71fe459244a727034f36ab3eb9",
|
"ledger/submissions.jsonl": "8a621da5637d481c7de4b4e3375f2a68cbdabf71fe459244a727034f36ab3eb9",
|
||||||
"outcomes/submissions.jsonl": "eaa6922265ab874d46282c8353419da53665ddca2baca53c5b4240e410666d50"
|
"outcomes/submissions.jsonl": "eaa6922265ab874d46282c8353419da53665ddca2baca53c5b4240e410666d50"
|
||||||
},
|
},
|
||||||
"generation": 5142,
|
"generation": 5143,
|
||||||
"phase": "cycle",
|
"phase": "cycle",
|
||||||
"schemaVersion": 1,
|
"schemaVersion": 1,
|
||||||
"updatedAt": "2026-09-10T11:39:51.958215+00:00",
|
"updatedAt": "2026-09-10T11:42:29.666385+00:00",
|
||||||
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
|
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
|
||||||
}
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user