state: generation 4969 (cycle)

This commit is contained in:
2026-09-10 05:20:36 +00:00
parent 91c445e336
commit 7c07dc1584
9 changed files with 1959 additions and 1961 deletions

View File

@@ -245,7 +245,7 @@
"ascend_910-b4|vllm|text-generation|model_type:qwen3_5_moe": { "ascend_910-b4|vllm|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe", "architectureSignature": "model_type:qwen3_5_moe",
"architectures": [], "architectures": [],
"evidenceCount": 4, "evidenceCount": 3,
"expiresAt": "2026-10-08T03:33:22+00:00", "expiresAt": "2026-10-08T03:33:22+00:00",
"framework": "vllm", "framework": "vllm",
"latestFailureAt": "2026-09-08T03:33:22+00:00", "latestFailureAt": "2026-09-08T03:33:22+00:00",
@@ -255,14 +255,12 @@
"sourceModelIds": [ "sourceModelIds": [
"mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B",
"mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B",
"apodex/Apodex-1.1-mini-GPTQ-Int4", "apodex/Apodex-1.1-mini-GPTQ-Int4"
"mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B"
], ],
"sourceTaskIds": [ "sourceTaskIds": [
"4478318", "4478318",
"4481796", "4481796",
"4421469", "4421469"
"4464042"
], ],
"targetGpu": "Ascend_910-b4", "targetGpu": "Ascend_910-b4",
"taskType": "text-generation" "taskType": "text-generation"
@@ -1325,7 +1323,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-10T05:17:57.890405+00:00", "generatedAt": "2026-09-10T05:20:35.932882+00:00",
"summary": { "summary": {
"activeBlockCount": 66, "activeBlockCount": 66,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -11,7 +11,7 @@
"1": { "1": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 354, "listingErrors": 355,
"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": 1, "nextAccountIndex": 2,
"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": "2026-09-10T05:17:57.866736+00:00", "updatedAt": "2026-09-10T05:20:35.909560+00:00",
"version": 1 "version": 1
} }

View File

@@ -416,7 +416,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T05:16:32.680107+00:00", "generatedAt": "2026-09-10T05:19:07.400510+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-10T04:54:16.505309+00:00", "generatedAt": "2026-09-10T05:18:58.948546+00:00",
"lastSyncTime": "2026-09-10T04:54:16.213468+00:00", "lastSyncTime": "2026-09-10T05:18:58.697138+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -249,7 +249,7 @@
"ascend_910-b4|vllm|text-generation|model_type:qwen3_5_moe": { "ascend_910-b4|vllm|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe", "architectureSignature": "model_type:qwen3_5_moe",
"architectures": [], "architectures": [],
"evidenceCount": 4, "evidenceCount": 3,
"expiresAt": "2026-10-08T03:33:22+00:00", "expiresAt": "2026-10-08T03:33:22+00:00",
"framework": "vllm", "framework": "vllm",
"latestFailureAt": "2026-09-08T03:33:22+00:00", "latestFailureAt": "2026-09-08T03:33:22+00:00",
@@ -259,14 +259,12 @@
"sourceModelIds": [ "sourceModelIds": [
"mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B",
"mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B",
"apodex/Apodex-1.1-mini-GPTQ-Int4", "apodex/Apodex-1.1-mini-GPTQ-Int4"
"mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B"
], ],
"sourceTaskIds": [ "sourceTaskIds": [
"4478318", "4478318",
"4481796", "4481796",
"4421469", "4421469"
"4464042"
], ],
"targetGpu": "Ascend_910-b4", "targetGpu": "Ascend_910-b4",
"taskType": "text-generation" "taskType": "text-generation"
@@ -1511,7 +1509,7 @@
"decisionSuccessRate": 0.04, "decisionSuccessRate": 0.04,
"decisionTotal": 25, "decisionTotal": 25,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 21, "ambiguous_runtime": 22,
"backend_operator": 2, "backend_operator": 2,
"framework_architecture_unsupported": 18, "framework_architecture_unsupported": 18,
"memory_capacity": 1, "memory_capacity": 1,
@@ -1519,18 +1517,18 @@
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 72, "failureCount": 73,
"failureRate": 0.9863, "failureRate": 0.9865,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 1,
"successRate": 0.0137, "successRate": 0.0135,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 73, "total": 74,
"unresolvedFailureCount": 48 "unresolvedFailureCount": 49
}, },
"Biren_166m|vllm|text-generation": { "Biren_166m|vllm|text-generation": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -1805,29 +1803,29 @@
"unresolvedFailureCount": 7 "unresolvedFailureCount": 7
}, },
"Iluvatar_mrv-100|unknown|text-generation": { "Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 68, "attributableFailureCount": 69,
"decisionFailureRate": 0.8718, "decisionFailureRate": 0.8734,
"decisionSuccessRate": 0.1282, "decisionSuccessRate": 0.1266,
"decisionTotal": 78, "decisionTotal": 79,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 17, "ambiguous_runtime": 17,
"framework_architecture_unsupported": 45, "framework_architecture_unsupported": 46,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 22, "model_load": 22,
"参数/模板问题": 2, "参数/模板问题": 2,
"验证失败": 47 "验证失败": 47
}, },
"failureCount": 134, "failureCount": 135,
"failureRate": 0.9306, "failureRate": 0.931,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 10, "successCount": 10,
"successRate": 0.0694, "successRate": 0.069,
"targetGpu": "Iluvatar_mrv-100", "targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation", "taskType": "text-generation",
"total": 144, "total": 145,
"unresolvedFailureCount": 66 "unresolvedFailureCount": 66
}, },
"Kunlunxin_p-800|unknown|text-generation": { "Kunlunxin_p-800|unknown|text-generation": {
@@ -2303,29 +2301,29 @@
"unresolvedFailureCount": 5 "unresolvedFailureCount": 5
}, },
"unknown": { "unknown": {
"attributableFailureCount": 120, "attributableFailureCount": 121,
"decisionFailureRate": 0.7143, "decisionFailureRate": 0.716,
"decisionSuccessRate": 0.2857, "decisionSuccessRate": 0.284,
"decisionTotal": 168, "decisionTotal": 169,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 101, "ambiguous_runtime": 102,
"backend_operator": 2, "backend_operator": 2,
"framework_architecture_unsupported": 86, "framework_architecture_unsupported": 87,
"memory_capacity": 5, "memory_capacity": 5,
"model_load": 24, "model_load": 24,
"tokenizer_compatibility": 3, "tokenizer_compatibility": 3,
"参数/模板问题": 56, "参数/模板问题": 56,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 950, "failureCount": 952,
"failureRate": 0.9519, "failureRate": 0.952,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 48, "successCount": 48,
"successRate": 0.0481, "successRate": 0.048,
"total": 998, "total": 1000,
"unresolvedFailureCount": 830 "unresolvedFailureCount": 831
}, },
"vllm": { "vllm": {
"attributableFailureCount": 230, "attributableFailureCount": 230,
@@ -2455,7 +2453,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-10T04:54:16.501434+00:00", "generatedAt": "2026-09-10T05:18:58.944414+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 26, "attributableFailureCount": 26,
@@ -2511,7 +2509,7 @@
"decisionSuccessRate": 0.0385, "decisionSuccessRate": 0.0385,
"decisionTotal": 26, "decisionTotal": 26,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 21, "ambiguous_runtime": 22,
"backend_operator": 2, "backend_operator": 2,
"framework_architecture_unsupported": 18, "framework_architecture_unsupported": 18,
"memory_capacity": 1, "memory_capacity": 1,
@@ -2519,15 +2517,15 @@
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 73, "failureCount": 74,
"failureRate": 0.9865, "failureRate": 0.9867,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 1,
"successRate": 0.0135, "successRate": 0.0133,
"total": 74, "total": 75,
"unresolvedFailureCount": 48 "unresolvedFailureCount": 49
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"attributableFailureCount": 20, "attributableFailureCount": 20,
@@ -2618,26 +2616,26 @@
"unresolvedFailureCount": 42 "unresolvedFailureCount": 42
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"attributableFailureCount": 68, "attributableFailureCount": 69,
"decisionFailureRate": 0.8718, "decisionFailureRate": 0.8734,
"decisionSuccessRate": 0.1282, "decisionSuccessRate": 0.1266,
"decisionTotal": 78, "decisionTotal": 79,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 17, "ambiguous_runtime": 17,
"framework_architecture_unsupported": 45, "framework_architecture_unsupported": 46,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 22, "model_load": 22,
"参数/模板问题": 2, "参数/模板问题": 2,
"验证失败": 47 "验证失败": 47
}, },
"failureCount": 134, "failureCount": 135,
"failureRate": 0.9306, "failureRate": 0.931,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 10, "successCount": 10,
"successRate": 0.0694, "successRate": 0.069,
"total": 144, "total": 145,
"unresolvedFailureCount": 66 "unresolvedFailureCount": 66
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
@@ -4035,25 +4033,25 @@
"decisionSuccessRate": 0.1111, "decisionSuccessRate": 0.1111,
"decisionTotal": 9, "decisionTotal": 9,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 5, "ambiguous_runtime": 6,
"backend_operator": 2, "backend_operator": 2,
"framework_architecture_unsupported": 5, "framework_architecture_unsupported": 5,
"model_load": 1 "model_load": 1
}, },
"failureCount": 13, "failureCount": 14,
"failureRate": 0.9286, "failureRate": 0.9333,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T00:20:21.332930+00:00", "lastTerminalAt": "2026-09-10T05:18:58.697138+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 1,
"successRate": 0.0714, "successRate": 0.0667,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 14, "total": 15,
"unresolvedFailureCount": 5 "unresolvedFailureCount": 6
}, },
"Cambricon_mlu-370-x4|unknown|text-generation": { "Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 4, "attributableFailureCount": 4,
@@ -4264,22 +4262,22 @@
"unresolvedFailureCount": 5 "unresolvedFailureCount": 5
}, },
"Iluvatar_mrv-100|unknown|text-generation": { "Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 15, "attributableFailureCount": 16,
"consecutiveFailures": 1, "consecutiveFailures": 2,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8333, "decisionFailureRate": 0.8421,
"decisionSuccessRate": 0.1667, "decisionSuccessRate": 0.1579,
"decisionTotal": 18, "decisionTotal": 19,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 2, "ambiguous_runtime": 1,
"framework_architecture_unsupported": 9, "framework_architecture_unsupported": 10,
"model_load": 6 "model_load": 6
}, },
"failureCount": 17, "failureCount": 17,
"failureRate": 0.85, "failureRate": 0.85,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T02:50:12.317748+00:00", "lastTerminalAt": "2026-09-10T05:18:58.697108+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -4288,7 +4286,7 @@
"targetGpu": "Iluvatar_mrv-100", "targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation", "taskType": "text-generation",
"total": 20, "total": 20,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 1
}, },
"Kunlunxin_p-800|unknown|text-generation": { "Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -6882,17 +6880,17 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1505, "terminalRecords": 1507,
"totalRecords": 1592, "totalRecords": 1594,
"totals": { "totals": {
"attributableFailureCount": 399, "attributableFailureCount": 400,
"decisionFailureRate": 0.8906, "decisionFailureRate": 0.8909,
"decisionSuccessRate": 0.1094, "decisionSuccessRate": 0.1091,
"decisionTotal": 448, "decisionTotal": 449,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 287, "ambiguous_runtime": 288,
"backend_operator": 29, "backend_operator": 29,
"framework_architecture_unsupported": 270, "framework_architecture_unsupported": 271,
"memory_capacity": 11, "memory_capacity": 11,
"model_load": 46, "model_load": 46,
"platform_infrastructure": 2, "platform_infrastructure": 2,
@@ -6902,21 +6900,21 @@
"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": 1456, "failureCount": 1458,
"failureRate": 0.9674, "failureRate": 0.9675,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 49, "successCount": 49,
"successRate": 0.0326, "successRate": 0.0325,
"total": 1505, "total": 1507,
"unresolvedFailureCount": 1055 "unresolvedFailureCount": 1056
}, },
"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。",
@@ -6924,7 +6922,7 @@
"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。",
@@ -6945,6 +6943,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1592, "summarizedRecords": 1594,
"version": 1 "version": 1
} }

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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-10T05:18:58.697108+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:13:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4609099", "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": "2026-09-10T05:18:58.697138+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:13:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610360", "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": "2026-09-10T04:54:16.213427+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:51:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493600", "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": "2026-09-10T04:54:16.213427+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:51:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493600", "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": "2026-09-10T04:54:16.213455+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:51:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505116", "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": "2026-09-10T04:54:16.213455+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:51:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505116", "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": "2026-09-10T04:54:16.213468+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:49:22+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505115", "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": "2026-09-10T04:54:16.213468+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:49:22+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505115", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-07T10:52:36.106605+00:00", "modelId": "poolside/Laguna-XS-2.1-INT4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:43:22+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4609106", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-07T10:52:36.106605+00:00", "modelId": "poolside/Laguna-XS-2.1-INT4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:43:22+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4609106", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm", "lastSyncTime": "2026-09-07T10:52:36.106615+00:00", "modelId": "Aimiliya0011/lora_4090", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:39:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4609107", "taskType": "text-generation", "verifyResult": -1} {"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm", "lastSyncTime": "2026-09-07T10:52:36.106615+00:00", "modelId": "Aimiliya0011/lora_4090", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:39:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4609107", "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, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-07T10:17:44.109315+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:11:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4464041", "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, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-07T10:17:44.109315+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:11:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4464041", "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, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-07T10:17:44.109293+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:09:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4464043", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-07T10:17:44.109327+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4464042", "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

View File

@@ -1,24 +1,24 @@
{ {
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "6ffa553dd767ec945ddd9cca33e61f77f9ade645cfe73b50267ea67f5605fd7c", ".modelhub_state/architecture_compatibility_blacklist.json": "f6bd9598f6600bca774036ad4db35da5a8c61a61baf8bdae9f9c2bdb8f6a3984",
".modelhub_state/architecture_history_backfill.json": "7fa444d9de899afa4cd1924dab50f37d8c39e86190f5a3f91961e8387aef0883", ".modelhub_state/architecture_history_backfill.json": "1f400b9f5763102d6a707f30db0a583e89df0b15a7e733098d50357863d48fd9",
".modelhub_state/market_intelligence.json": "bc70a54ef179cda621c28fc5ba060771dda3985e4f5c90d35f977af4894f98be", ".modelhub_state/market_intelligence.json": "9dd23bb5eecc8b4fe73d34df23f5405f197e7d5735d85e2de931cd101ef3e75c",
".modelhub_state/official_capabilities.json": "69d506765a4c6418d5e453ed57656991a38972cdda366921eb12cb85eddc1512", ".modelhub_state/official_capabilities.json": "de3c45d515804fe2728f687f33a9177115a47f861a2285b843e04e3380bbdf47",
".modelhub_state/outcome_checkpoint.json": "3183debd727a9e378747a368604add80a8cd9b00b21b89fedba50bde13eea8a7", ".modelhub_state/outcome_checkpoint.json": "f5d257af6f315b59e60e355f67b1928c729e003691fb27fc28bb4725c893e94e",
".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99", ".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99",
".modelhub_state/recent_outcomes.jsonl": "32af73424b4be028f2a6e49d00894db9a79745ed8743d28d97eb1e4d68408601", ".modelhub_state/recent_outcomes.jsonl": "88134eeed7ec37b7d382c16a4ea2e09ea59789171acf04ee2cbe99e0d82350ba",
".modelhub_state/recovery_active_tasks.jsonl": "68e6e6811ecebfe61c1e9e2572aea209c76ff3451ff325ede25d1e0a735782f2", ".modelhub_state/recovery_active_tasks.jsonl": "6918fbfc22dd1fd3f2cac84eef9061e5632748fe4947eab7b600a196324578e8",
".modelhub_state/recovery_intents.jsonl": "90d3a5342a2c4ba16b891d8b632ccd12368a2eab710efcfa770772ee30c28287", ".modelhub_state/recovery_intents.jsonl": "c7a6cb21bf21cf9f88826a2ab8e7312f638b415a9920300aa49b0500e5eacc8d",
".modelhub_state/routing_intelligence.json": "8a6576cd380d1c0ee7312052476121154d068841a96e875834f529655753cb3c", ".modelhub_state/routing_intelligence.json": "8a6576cd380d1c0ee7312052476121154d068841a96e875834f529655753cb3c",
".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": "90ea366621a446575de127a2a40ca9935dfee4491aba2d02052fda81d90cd6e6", "ledger/submissions.jsonl": "90ea366621a446575de127a2a40ca9935dfee4491aba2d02052fda81d90cd6e6",
"outcomes/submissions.jsonl": "3494406c2b92efa3bf2af64d4906c325304eeaa6cbd30083f0310637da46df71" "outcomes/submissions.jsonl": "3494406c2b92efa3bf2af64d4906c325304eeaa6cbd30083f0310637da46df71"
}, },
"generation": 4968, "generation": 4969,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-10T05:17:58.015618+00:00", "updatedAt": "2026-09-10T05:20:36.829319+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977" "writerId": "58ff5dc2a2d64b119ad1e4560700f977"
} }