state: generation 11680 (cycle_no_slots)

This commit is contained in:
2026-09-21 20:01:09 +00:00
parent 501ff027f7
commit 098fad3114
7 changed files with 1826 additions and 1877 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T19:58:46.334949+00:00",
"lastSyncTime": "2026-09-21T19:58:46.051807+00:00",
"generatedAt": "2026-09-21T20:00:56.068833+00:00",
"lastSyncTime": "2026-09-21T20:00:55.754450+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3509,12 +3509,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 21,
"failureBreakdown": {
"ambiguous_runtime": 19,
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 20,
"memory_capacity": 1,
"参数/模板问题": 12
},
"failureCount": 52,
"failureCount": 53,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -3524,8 +3524,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 52,
"unresolvedFailureCount": 31
"total": 53,
"unresolvedFailureCount": 32
},
"Iluvatar_bi-100|transformers|text-generation": {
"attributableFailureCount": 0,
@@ -5464,7 +5464,7 @@
"decisionSuccessRate": 0.0242,
"decisionTotal": 3632,
"failureBreakdown": {
"ambiguous_runtime": 1497,
"ambiguous_runtime": 1498,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5478,15 +5478,15 @@
"tokenizer_compatibility": 412,
"参数/模板问题": 46
},
"failureCount": 5952,
"failureCount": 5953,
"failureRate": 0.9854,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 88,
"successRate": 0.0146,
"total": 6040,
"unresolvedFailureCount": 1543
"total": 6041,
"unresolvedFailureCount": 1544
},
"vllm-customized": {
"attributableFailureCount": 6,
@@ -5632,7 +5632,7 @@
"unresolvedFailureCount": 108
}
},
"generatedAt": "2026-09-21T19:58:46.321250+00:00",
"generatedAt": "2026-09-21T20:00:56.021563+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5753,7 +5753,7 @@
"decisionSuccessRate": 0.2121,
"decisionTotal": 66,
"failureBreakdown": {
"ambiguous_runtime": 109,
"ambiguous_runtime": 110,
"framework_architecture_unsupported": 43,
"memory_capacity": 4,
"model_load": 3,
@@ -5761,15 +5761,15 @@
"参数/模板问题": 34,
"验证失败": 22
},
"failureCount": 217,
"failureRate": 0.9394,
"failureCount": 218,
"failureRate": 0.9397,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.0606,
"total": 231,
"unresolvedFailureCount": 165
"successRate": 0.0603,
"total": 232,
"unresolvedFailureCount": 166
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
@@ -10514,9 +10514,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "gemma2",
@@ -10528,8 +10528,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm|text-generation|gemma4_unified|none": {
"attributableFailureCount": 1,
@@ -17910,31 +17910,6 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"repository_structure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T16:21:18.661407+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -19278,12 +19253,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T17:22:47.256780+00:00",
"lastTerminalAt": "2026-09-21T20:00:55.754450+00:00",
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -19293,8 +19268,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm|text-generation|gemma4_unified|none": {
"attributableFailureCount": 1,
@@ -21199,31 +21174,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|mpt|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"repository_structure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-21T16:21:18.661407+00:00",
"modelType": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|gemma3|compressed-tensors": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -27959,9 +27909,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
@@ -27974,8 +27924,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm|text-generation|gemma4_unified|none|33": {
"attributableFailureCount": 1,
@@ -37769,15 +37719,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16392,
"totalRecords": 16586,
"terminalRecords": 16393,
"totalRecords": 16587,
"totals": {
"attributableFailureCount": 5911,
"decisionFailureRate": 0.862,
"decisionSuccessRate": 0.138,
"decisionTotal": 6857,
"failureBreakdown": {
"ambiguous_runtime": 4026,
"ambiguous_runtime": 4027,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 104,
@@ -37793,31 +37743,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15446,
"failureCount": 15447,
"failureRate": 0.9423,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 946,
"successRate": 0.0577,
"total": 16392,
"unresolvedFailureCount": 8610
"total": 16393,
"unresolvedFailureCount": 8611
},
"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 MetaX_c-500 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。",
@@ -37857,6 +37807,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16586,
"summarizedRecords": 16587,
"version": 1
}