state: generation 11202 (cycle)

This commit is contained in:
2026-09-21 05:14:35 +00:00
parent 4c5c9b04bb
commit 96b456a6d3
9 changed files with 1909 additions and 1790 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T05:07:18.736989+00:00",
"lastSyncTime": "2026-09-21T05:07:16.468567+00:00",
"generatedAt": "2026-09-21T05:14:26.473344+00:00",
"lastSyncTime": "2026-09-21T05:14:26.178418+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3310,9 +3310,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 35
"ambiguous_runtime": 37
},
"failureCount": 35,
"failureCount": 37,
"failureRate": 1.0,
"framework": "transformers",
"pendingCount": 0,
@@ -3322,8 +3322,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 35,
"unresolvedFailureCount": 35
"total": 37,
"unresolvedFailureCount": 37
},
"Iluvatar_bi-100|unknown|feature_emb": {
"attributableFailureCount": 0,
@@ -5184,21 +5184,21 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 44,
"ambiguous_runtime": 46,
"framework_architecture_unsupported": 7,
"memory_capacity": 5,
"model_load": 2,
"tokenizer_compatibility": 8
},
"failureCount": 66,
"failureCount": 68,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 66,
"unresolvedFailureCount": 44
"total": 68,
"unresolvedFailureCount": 46
},
"unknown": {
"attributableFailureCount": 1858,
@@ -5399,7 +5399,7 @@
"unresolvedFailureCount": 67
}
},
"generatedAt": "2026-09-21T05:07:18.725383+00:00",
"generatedAt": "2026-09-21T05:14:26.462904+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 91,
@@ -5544,22 +5544,22 @@
"decisionSuccessRate": 0.2392,
"decisionTotal": 255,
"failureBreakdown": {
"ambiguous_runtime": 155,
"ambiguous_runtime": 157,
"memory_capacity": 194,
"platform_infrastructure": 635,
"参数/模板问题": 242,
"日志缺失": 134,
"验证失败": 20
},
"failureCount": 1380,
"failureCount": 1382,
"failureRate": 0.9577,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 635,
"successCount": 61,
"successRate": 0.0423,
"total": 1441,
"unresolvedFailureCount": 551
"total": 1443,
"unresolvedFailureCount": 553
},
"Iluvatar_bi-150": {
"attributableFailureCount": 739,
@@ -9304,6 +9304,52 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_vl|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"modelType": "qwen3_vl",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-100|transformers|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|transformers|text-generation|gemma4|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
@@ -14814,6 +14860,31 @@
"total": 20,
"unresolvedFailureCount": 10
},
"Iluvatar_bi-100|transformers|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "transformers",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T05:14:26.178403+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|transformers|text-generation": {
"attributableFailureCount": 14,
"consecutiveFailures": 14,
@@ -15009,9 +15080,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 4
},
"failureCount": 5,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -15023,8 +15094,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 4,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 8,
@@ -15184,25 +15255,25 @@
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.5,
"decisionSuccessRate": 0.5,
"decisionTotal": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 0.5,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T03:29:39.969809+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.5,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 2,
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm|text-generation": {
@@ -16891,6 +16962,56 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_vl|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"lastTerminalAt": "2026-09-21T05:14:26.178418+00:00",
"modelType": "qwen3_vl",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-100|transformers|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"lastTerminalAt": "2026-09-21T05:14:26.178403+00:00",
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|transformers|text-generation|gemma4|none": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
@@ -18445,31 +18566,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|hy_v3|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-20T20:49:19.683345+00:00",
"modelType": "hy_v3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|hyperclovax_vision_v2|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -18893,29 +18989,6 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|llama|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-21T01:35:45.556154+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -24067,6 +24140,54 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_vl|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_vl",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-100|transformers|text-generation|sophia_hybrid|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"loadSizeLog2Bucket": 31,
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|transformers|text-generation|gemma4|none|32": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
@@ -31703,15 +31824,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16132,
"totalRecords": 16313,
"terminalRecords": 16134,
"totalRecords": 16315,
"totals": {
"attributableFailureCount": 5854,
"decisionFailureRate": 0.8616,
"decisionSuccessRate": 0.1384,
"decisionTotal": 6794,
"failureBreakdown": {
"ambiguous_runtime": 3861,
"ambiguous_runtime": 3863,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
@@ -31727,15 +31848,15 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15192,
"failureCount": 15194,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 923,
"successCount": 940,
"successRate": 0.0583,
"total": 16132,
"unresolvedFailureCount": 8415
"total": 16134,
"unresolvedFailureCount": 8417
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -31744,14 +31865,14 @@
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-100 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-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 Cambricon_mlu-370-x4 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-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 Ascend_910-b4 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 Ascend_910-b3 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 hygon_k100-ai 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。",
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -31790,6 +31911,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16313,
"summarizedRecords": 16315,
"version": 1
}