state: generation 5034 (cycle)

This commit is contained in:
2026-09-10 06:58:04 +00:00
parent 1d23fd92c7
commit 2396ab497f
9 changed files with 2071 additions and 2072 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T06:40:56.332322+00:00",
"lastSyncTime": "2026-09-10T06:40:56.094753+00:00",
"generatedAt": "2026-09-10T06:56:24.262905+00:00",
"lastSyncTime": "2026-09-10T06:56:22.046035+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -584,7 +584,7 @@
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
"evidenceCount": 3,
"evidenceCount": 2,
"expiresAt": "2026-10-07T23:51:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-07T23:51:21+00:00",
@@ -593,13 +593,11 @@
"modelType": "qwen3_5_moe",
"sourceModelIds": [
"mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B",
"mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B",
"mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B"
"mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B"
],
"sourceTaskIds": [
"4479115",
"4482387",
"4462837"
"4482387"
],
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation"
@@ -1553,24 +1551,24 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 17,
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 76,
"failureRate": 0.9744,
"failureCount": 77,
"failureRate": 0.9747,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0256,
"successRate": 0.0253,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 78,
"unresolvedFailureCount": 56
"total": 79,
"unresolvedFailureCount": 57
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 7,
@@ -2149,12 +2147,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 49,
"ambiguous_runtime": 50,
"framework_architecture_unsupported": 38,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 93,
"failureCount": 94,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2164,8 +2162,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 93,
"unresolvedFailureCount": 49
"total": 94,
"unresolvedFailureCount": 50
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -2302,7 +2300,7 @@
"decisionSuccessRate": 0.284,
"decisionTotal": 169,
"failureBreakdown": {
"ambiguous_runtime": 105,
"ambiguous_runtime": 106,
"backend_operator": 2,
"framework_architecture_unsupported": 87,
"memory_capacity": 5,
@@ -2311,15 +2309,15 @@
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 955,
"failureRate": 0.9521,
"failureCount": 956,
"failureRate": 0.9522,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 48,
"successRate": 0.0479,
"total": 1003,
"unresolvedFailureCount": 834
"successRate": 0.0478,
"total": 1004,
"unresolvedFailureCount": 835
},
"vllm": {
"attributableFailureCount": 230,
@@ -2327,7 +2325,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 230,
"failureBreakdown": {
"ambiguous_runtime": 147,
"ambiguous_runtime": 148,
"backend_operator": 24,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2338,15 +2336,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 399,
"failureCount": 400,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 399,
"unresolvedFailureCount": 168
"total": 400,
"unresolvedFailureCount": 169
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2449,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T06:40:56.328362+00:00",
"generatedAt": "2026-09-10T06:56:24.258540+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2529,21 +2527,21 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 17,
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 76,
"failureRate": 0.9744,
"failureCount": 77,
"failureRate": 0.9747,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0256,
"total": 78,
"unresolvedFailureCount": 56
"successRate": 0.0253,
"total": 79,
"unresolvedFailureCount": 57
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 17,
@@ -2733,22 +2731,22 @@
"decisionSuccessRate": 0.2167,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 50,
"ambiguous_runtime": 51,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 240,
"failureRate": 0.9486,
"failureCount": 241,
"failureRate": 0.9488,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0514,
"total": 253,
"unresolvedFailureCount": 193
"successRate": 0.0512,
"total": 254,
"unresolvedFailureCount": 194
},
"hygon_k100-ai": {
"attributableFailureCount": 38,
@@ -4050,22 +4048,22 @@
"unresolvedFailureCount": 8
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 4,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 6,
"decisionFailureRate": 0.6,
"decisionSuccessRate": 0.4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 3,
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 2,
"tokenizer_compatibility": 1
},
"failureCount": 8,
"failureRate": 0.8,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T02:40:44.943974+00:00",
"lastTerminalAt": "2026-09-10T06:56:22.046014+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4074,7 +4072,7 @@
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 10,
"unresolvedFailureCount": 4
"unresolvedFailureCount": 5
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 2,
@@ -4565,21 +4563,21 @@
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 3
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 2
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T06:03:48.106911+00:00",
"lastTerminalAt": "2026-09-10T06:56:22.046035+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4588,7 +4586,7 @@
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 17
"unresolvedFailureCount": 18
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -4641,19 +4639,19 @@
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 9,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 7,
"framework_architecture_unsupported": 6,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 17,
"failureCount": 16,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4665,7 +4663,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 17,
"total": 16,
"unresolvedFailureCount": 8
}
},
@@ -6899,15 +6897,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1521,
"totalRecords": 1608,
"terminalRecords": 1523,
"totalRecords": 1610,
"totals": {
"attributableFailureCount": 400,
"decisionFailureRate": 0.8909,
"decisionSuccessRate": 0.1091,
"decisionTotal": 449,
"failureBreakdown": {
"ambiguous_runtime": 302,
"ambiguous_runtime": 304,
"backend_operator": 29,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -6919,21 +6917,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1472,
"failureCount": 1474,
"failureRate": 0.9678,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0322,
"total": 1521,
"unresolvedFailureCount": 1070
"total": 1523,
"unresolvedFailureCount": 1072
},
"warnings": [
"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 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 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。",
@@ -6941,7 +6939,7 @@
"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 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 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。",
@@ -6962,6 +6960,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1608,
"summarizedRecords": 1610,
"version": 1
}