state: generation 11735 (cycle_no_slots)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-21T20:41:43.625847+00:00",
|
||||
"lastSyncTime": "2026-09-21T20:41:43.555774+00:00",
|
||||
"generatedAt": "2026-09-21T20:43:08.684873+00:00",
|
||||
"lastSyncTime": "2026-09-21T20:43:08.365510+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -4503,28 +4503,28 @@
|
||||
"unresolvedFailureCount": 114
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 17,
|
||||
"decisionFailureRate": 0.9444,
|
||||
"decisionSuccessRate": 0.0556,
|
||||
"decisionTotal": 18,
|
||||
"attributableFailureCount": 18,
|
||||
"decisionFailureRate": 0.9474,
|
||||
"decisionSuccessRate": 0.0526,
|
||||
"decisionTotal": 19,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"backend_operator": 1,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"repository_structure": 2,
|
||||
"参数/模板问题": 13
|
||||
},
|
||||
"failureCount": 31,
|
||||
"failureRate": 0.9688,
|
||||
"failureCount": 32,
|
||||
"failureRate": 0.9697,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0312,
|
||||
"successRate": 0.0303,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 32,
|
||||
"total": 33,
|
||||
"unresolvedFailureCount": 14
|
||||
},
|
||||
"Kunlunxin_p-800|vllm|text-generation": {
|
||||
@@ -5652,13 +5652,13 @@
|
||||
"unresolvedFailureCount": 212
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 77,
|
||||
"decisionFailureRate": 0.9625,
|
||||
"decisionSuccessRate": 0.0375,
|
||||
"decisionTotal": 80,
|
||||
"attributableFailureCount": 78,
|
||||
"decisionFailureRate": 0.963,
|
||||
"decisionSuccessRate": 0.037,
|
||||
"decisionTotal": 81,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 88,
|
||||
"backend_operator": 1,
|
||||
"backend_operator": 2,
|
||||
"context_length": 3,
|
||||
"framework_architecture_unsupported": 66,
|
||||
"memory_capacity": 1,
|
||||
@@ -5668,18 +5668,18 @@
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 27
|
||||
},
|
||||
"failureCount": 193,
|
||||
"failureRate": 0.9847,
|
||||
"failureCount": 194,
|
||||
"failureRate": 0.9848,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 3,
|
||||
"successRate": 0.0153,
|
||||
"total": 196,
|
||||
"successRate": 0.0152,
|
||||
"total": 197,
|
||||
"unresolvedFailureCount": 115
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T20:41:43.615367+00:00",
|
||||
"generatedAt": "2026-09-21T20:43:08.673957+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 99,
|
||||
@@ -5904,13 +5904,13 @@
|
||||
"unresolvedFailureCount": 716
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"attributableFailureCount": 19,
|
||||
"decisionFailureRate": 0.95,
|
||||
"decisionSuccessRate": 0.05,
|
||||
"decisionTotal": 20,
|
||||
"attributableFailureCount": 20,
|
||||
"decisionFailureRate": 0.9524,
|
||||
"decisionSuccessRate": 0.0476,
|
||||
"decisionTotal": 21,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 188,
|
||||
"backend_operator": 1,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 15,
|
||||
"memory_capacity": 1,
|
||||
"repository_structure": 2,
|
||||
@@ -5918,14 +5918,14 @@
|
||||
"日志缺失": 1,
|
||||
"验证失败": 23
|
||||
},
|
||||
"failureCount": 251,
|
||||
"failureCount": 252,
|
||||
"failureRate": 0.996,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.004,
|
||||
"total": 252,
|
||||
"total": 253,
|
||||
"unresolvedFailureCount": 232
|
||||
},
|
||||
"Kunlunxin_r-200-8f": {
|
||||
@@ -15112,6 +15112,29 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "starcoder2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Kunlunxin_p-800|vllm|text-generation|deepseek_v4|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -18095,6 +18118,31 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-21T20:43:08.365510+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,
|
||||
@@ -18155,11 +18203,11 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4,
|
||||
"ambiguous_runtime": 3,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"runtime_memory": 1
|
||||
},
|
||||
"failureCount": 7,
|
||||
"failureCount": 6,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -18171,8 +18219,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation",
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 4
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Sunrise_pt-200-x1|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -21285,6 +21333,31 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastTerminalAt": "2026-09-21T20:43:08.365510+00:00",
|
||||
"modelType": "starcoder2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"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,
|
||||
@@ -21335,31 +21408,6 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation|gemma3|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastTerminalAt": "2026-09-21T10:57:20.777339+00:00",
|
||||
"modelType": "gemma3",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation|llama|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -34574,6 +34622,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
"modelType": "starcoder2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Kunlunxin_p-800|vllm|text-generation|deepseek_v4|none|36": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -38116,18 +38188,18 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16410,
|
||||
"totalRecords": 16604,
|
||||
"terminalRecords": 16411,
|
||||
"totalRecords": 16605,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5918,
|
||||
"attributableFailureCount": 5919,
|
||||
"decisionFailureRate": 0.8621,
|
||||
"decisionSuccessRate": 0.1379,
|
||||
"decisionTotal": 6865,
|
||||
"decisionTotal": 6866,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4036,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 104,
|
||||
"backend_operator": 105,
|
||||
"context_length": 321,
|
||||
"framework_architecture_unsupported": 2092,
|
||||
"memory_capacity": 1199,
|
||||
@@ -38140,31 +38212,31 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 674
|
||||
},
|
||||
"failureCount": 15463,
|
||||
"failureCount": 15464,
|
||||
"failureRate": 0.9423,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 925,
|
||||
"successCount": 947,
|
||||
"successRate": 0.0577,
|
||||
"total": 16410,
|
||||
"total": 16411,
|
||||
"unresolvedFailureCount": 8620
|
||||
},
|
||||
"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。",
|
||||
@@ -38204,6 +38276,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16604,
|
||||
"summarizedRecords": 16605,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user