state: generation 11922 (cycle_no_slots)

This commit is contained in:
2026-09-21 23:47:30 +00:00
parent 8391de4f0f
commit fc7c1386a9
7 changed files with 2254 additions and 2186 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T23:42:47.613650+00:00",
"lastSyncTime": "2026-09-21T23:42:47.252222+00:00",
"generatedAt": "2026-09-21T23:47:10.105504+00:00",
"lastSyncTime": "2026-09-21T23:47:09.753992+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3181,13 +3181,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 24,
"failureBreakdown": {
"ambiguous_runtime": 46,
"ambiguous_runtime": 47,
"framework_architecture_unsupported": 23,
"platform_infrastructure": 1,
"repository_structure": 1,
"参数/模板问题": 6
},
"failureCount": 77,
"failureCount": 78,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -3197,8 +3197,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 77,
"unresolvedFailureCount": 52
"total": 78,
"unresolvedFailureCount": 53
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 204,
@@ -3526,12 +3526,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 4,
"model_load": 2,
"参数/模板问题": 4
},
"failureCount": 20,
"failureCount": 21,
"failureRate": 1.0,
"framework": "vllm-customized",
"pendingCount": 0,
@@ -3541,8 +3541,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 14
"total": 21,
"unresolvedFailureCount": 15
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 13,
@@ -5562,20 +5562,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 4,
"model_load": 2,
"参数/模板问题": 4
},
"failureCount": 20,
"failureCount": 21,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 20,
"unresolvedFailureCount": 14
"total": 21,
"unresolvedFailureCount": 15
},
"vllm-mlu": {
"attributableFailureCount": 21,
@@ -5678,7 +5678,7 @@
"decisionSuccessRate": 0.0482,
"decisionTotal": 83,
"failureBreakdown": {
"ambiguous_runtime": 92,
"ambiguous_runtime": 93,
"backend_operator": 2,
"context_length": 3,
"framework_architecture_unsupported": 66,
@@ -5689,18 +5689,18 @@
"tokenizer_compatibility": 2,
"参数/模板问题": 28
},
"failureCount": 200,
"failureRate": 0.9804,
"failureCount": 201,
"failureRate": 0.9805,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 4,
"successRate": 0.0196,
"total": 204,
"unresolvedFailureCount": 120
"successRate": 0.0195,
"total": 205,
"unresolvedFailureCount": 121
}
},
"generatedAt": "2026-09-21T23:42:47.602690+00:00",
"generatedAt": "2026-09-21T23:47:10.094226+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5734,7 +5734,7 @@
"decisionSuccessRate": 0.1636,
"decisionTotal": 385,
"failureBreakdown": {
"ambiguous_runtime": 182,
"ambiguous_runtime": 183,
"context_length": 1,
"framework_architecture_unsupported": 178,
"memory_capacity": 19,
@@ -5746,15 +5746,15 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 963,
"failureRate": 0.9386,
"failureCount": 964,
"failureRate": 0.9387,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 63,
"successRate": 0.0614,
"total": 1026,
"unresolvedFailureCount": 639
"successRate": 0.0613,
"total": 1027,
"unresolvedFailureCount": 640
},
"Biren_166m": {
"attributableFailureCount": 186,
@@ -5821,7 +5821,7 @@
"decisionSuccessRate": 0.209,
"decisionTotal": 67,
"failureBreakdown": {
"ambiguous_runtime": 110,
"ambiguous_runtime": 111,
"framework_architecture_unsupported": 44,
"memory_capacity": 4,
"model_load": 3,
@@ -5829,15 +5829,15 @@
"参数/模板问题": 34,
"验证失败": 22
},
"failureCount": 219,
"failureRate": 0.9399,
"failureCount": 220,
"failureRate": 0.9402,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.0601,
"total": 233,
"unresolvedFailureCount": 166
"successRate": 0.0598,
"total": 234,
"unresolvedFailureCount": 167
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
@@ -7402,9 +7402,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 7
"ambiguous_runtime": 8
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "llama",
@@ -7416,8 +7416,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 7
"total": 8,
"unresolvedFailureCount": 8
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none": {
"attributableFailureCount": 0,
@@ -9837,6 +9837,29 @@
"total": 5,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|awq": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -17855,9 +17878,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -17869,8 +17892,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 0,
@@ -18035,11 +18058,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 8,
"model_load": 2,
"参数/模板问题": 4
},
"failureCount": 13,
"failureCount": 14,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastPlatformFailureAt": null,
@@ -18051,8 +18074,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 11
"total": 14,
"unresolvedFailureCount": 12
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 0,
@@ -18161,21 +18184,20 @@
"unresolvedFailureCount": 5
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 5,
"backend_operator": 1,
"framework_architecture_unsupported": 1,
"memory_capacity": 1,
"model_load": 1,
"参数/模板问题": 1
},
"failureCount": 10,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"lastPlatformFailureAt": null,
@@ -18187,7 +18209,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 10,
"total": 9,
"unresolvedFailureCount": 6
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": {
@@ -18586,9 +18608,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-21T19:49:37.657119+00:00",
@@ -18601,8 +18623,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Ascend_910-b4|vllm|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0,
@@ -19433,6 +19455,31 @@
"total": 5,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|awq": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastTerminalAt": "2026-09-21T23:47:09.753992+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -19740,9 +19787,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 7
"ambiguous_runtime": 6
},
"failureCount": 7,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T17:22:47.256939+00:00",
@@ -19755,8 +19802,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 7
"total": 6,
"unresolvedFailureCount": 6
},
"Cambricon_mlu-370-x8|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
@@ -20684,31 +20731,6 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|bailing_hybrid|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"memory_capacity": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"lastTerminalAt": "2026-09-20T12:21:49.901701+00:00",
"modelType": "bailing_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|gemma4_unified|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -23545,6 +23567,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -27111,6 +27157,30 @@
"total": 2,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|awq|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors|27": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -38551,15 +38621,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16439,
"totalRecords": 16633,
"terminalRecords": 16441,
"totalRecords": 16635,
"totals": {
"attributableFailureCount": 5925,
"decisionFailureRate": 0.8619,
"decisionSuccessRate": 0.1381,
"decisionTotal": 6874,
"failureBreakdown": {
"ambiguous_runtime": 4052,
"ambiguous_runtime": 4054,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 105,
@@ -38575,31 +38645,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15490,
"failureCount": 15492,
"failureRate": 0.9423,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 949,
"successRate": 0.0577,
"total": 16439,
"unresolvedFailureCount": 8640
"total": 16441,
"unresolvedFailureCount": 8642
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Kunlunxin_p-800 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 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 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。",
"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。",
@@ -38639,6 +38709,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16633,
"summarizedRecords": 16635,
"version": 1
}